import pandas as pd
import datetime as dt
import numpy as np
import requests
import tweepy
import json
import re
import time

dog = pd.read_csv('twitter-archive-enhanced.csv',encoding='latin-1')

dog.head(10)

dog.info

<bound method DataFrame.info of                 tweet_id  in_reply_to_status_id  in_reply_to_user_id  \
0     892420643555336193                    NaN                  NaN   
1     892177421306343426                    NaN                  NaN   
2     891815181378084864                    NaN                  NaN   
3     891689557279858688                    NaN                  NaN   
4     891327558926688256                    NaN                  NaN   
5     891087950875897856                    NaN                  NaN   
6     890971913173991426                    NaN                  NaN   
7     890729181411237888                    NaN                  NaN   
8     890609185150312448                    NaN                  NaN   
9     890240255349198849                    NaN                  NaN   
10    890006608113172480                    NaN                  NaN   
11    889880896479866881                    NaN                  NaN   
12    889665388333682689                    NaN                  NaN   
13    889638837579907072                    NaN                  NaN   
14    889531135344209921                    NaN                  NaN   
15    889278841981685760                    NaN                  NaN   
16    888917238123831296                    NaN                  NaN   
17    888804989199671297                    NaN                  NaN   
18    888554962724278272                    NaN                  NaN   
19    888202515573088257                    NaN                  NaN   
20    888078434458587136                    NaN                  NaN   
21    887705289381826560                    NaN                  NaN   
22    887517139158093824                    NaN                  NaN   
23    887473957103951883                    NaN                  NaN   
24    887343217045368832                    NaN                  NaN   
25    887101392804085760                    NaN                  NaN   
26    886983233522544640                    NaN                  NaN   
27    886736880519319552                    NaN                  NaN   
28    886680336477933568                    NaN                  NaN   
29    886366144734445568                    NaN                  NaN   
...                  ...                    ...                  ...   
2326  666411507551481857                    NaN                  NaN   
2327  666407126856765440                    NaN                  NaN   
2328  666396247373291520                    NaN                  NaN   
2329  666373753744588802                    NaN                  NaN   
2330  666362758909284353                    NaN                  NaN   
2331  666353288456101888                    NaN                  NaN   
2332  666345417576210432                    NaN                  NaN   
2333  666337882303524864                    NaN                  NaN   
2334  666293911632134144                    NaN                  NaN   
2335  666287406224695296                    NaN                  NaN   
2336  666273097616637952                    NaN                  NaN   
2337  666268910803644416                    NaN                  NaN   
2338  666104133288665088                    NaN                  NaN   
2339  666102155909144576                    NaN                  NaN   
2340  666099513787052032                    NaN                  NaN   
2341  666094000022159362                    NaN                  NaN   
2342  666082916733198337                    NaN                  NaN   
2343  666073100786774016                    NaN                  NaN   
2344  666071193221509120                    NaN                  NaN   
2345  666063827256086533                    NaN                  NaN   
2346  666058600524156928                    NaN                  NaN   
2347  666057090499244032                    NaN                  NaN   
2348  666055525042405380                    NaN                  NaN   
2349  666051853826850816                    NaN                  NaN   
2350  666050758794694657                    NaN                  NaN   
2351  666049248165822465                    NaN                  NaN   
2352  666044226329800704                    NaN                  NaN   
2353  666033412701032449                    NaN                  NaN   
2354  666029285002620928                    NaN                  NaN   
2355  666020888022790149                    NaN                  NaN   

                      timestamp  \
0     2017-08-01 16:23:56 +0000   
1     2017-08-01 00:17:27 +0000   
2     2017-07-31 00:18:03 +0000   
3     2017-07-30 15:58:51 +0000   
4     2017-07-29 16:00:24 +0000   
5     2017-07-29 00:08:17 +0000   
6     2017-07-28 16:27:12 +0000   
7     2017-07-28 00:22:40 +0000   
8     2017-07-27 16:25:51 +0000   
9     2017-07-26 15:59:51 +0000   
10    2017-07-26 00:31:25 +0000   
11    2017-07-25 16:11:53 +0000   
12    2017-07-25 01:55:32 +0000   
13    2017-07-25 00:10:02 +0000   
14    2017-07-24 17:02:04 +0000   
15    2017-07-24 00:19:32 +0000   
16    2017-07-23 00:22:39 +0000   
17    2017-07-22 16:56:37 +0000   
18    2017-07-22 00:23:06 +0000   
19    2017-07-21 01:02:36 +0000   
20    2017-07-20 16:49:33 +0000   
21    2017-07-19 16:06:48 +0000   
22    2017-07-19 03:39:09 +0000   
23    2017-07-19 00:47:34 +0000   
24    2017-07-18 16:08:03 +0000   
25    2017-07-18 00:07:08 +0000   
26    2017-07-17 16:17:36 +0000   
27    2017-07-16 23:58:41 +0000   
28    2017-07-16 20:14:00 +0000   
29    2017-07-15 23:25:31 +0000   
...                         ...   
2326  2015-11-17 00:24:19 +0000   
2327  2015-11-17 00:06:54 +0000   
2328  2015-11-16 23:23:41 +0000   
2329  2015-11-16 21:54:18 +0000   
2330  2015-11-16 21:10:36 +0000   
2331  2015-11-16 20:32:58 +0000   
2332  2015-11-16 20:01:42 +0000   
2333  2015-11-16 19:31:45 +0000   
2334  2015-11-16 16:37:02 +0000   
2335  2015-11-16 16:11:11 +0000   
2336  2015-11-16 15:14:19 +0000   
2337  2015-11-16 14:57:41 +0000   
2338  2015-11-16 04:02:55 +0000   
2339  2015-11-16 03:55:04 +0000   
2340  2015-11-16 03:44:34 +0000   
2341  2015-11-16 03:22:39 +0000   
2342  2015-11-16 02:38:37 +0000   
2343  2015-11-16 01:59:36 +0000   
2344  2015-11-16 01:52:02 +0000   
2345  2015-11-16 01:22:45 +0000   
2346  2015-11-16 01:01:59 +0000   
2347  2015-11-16 00:55:59 +0000   
2348  2015-11-16 00:49:46 +0000   
2349  2015-11-16 00:35:11 +0000   
2350  2015-11-16 00:30:50 +0000   
2351  2015-11-16 00:24:50 +0000   
2352  2015-11-16 00:04:52 +0000   
2353  2015-11-15 23:21:54 +0000   
2354  2015-11-15 23:05:30 +0000   
2355  2015-11-15 22:32:08 +0000   

                                                 source  \
0     <a href="http://twitter.com/download/iphone" r...   
1     <a href="http://twitter.com/download/iphone" r...   
2     <a href="http://twitter.com/download/iphone" r...   
3     <a href="http://twitter.com/download/iphone" r...   
4     <a href="http://twitter.com/download/iphone" r...   
5     <a href="http://twitter.com/download/iphone" r...   
6     <a href="http://twitter.com/download/iphone" r...   
7     <a href="http://twitter.com/download/iphone" r...   
8     <a href="http://twitter.com/download/iphone" r...   
9     <a href="http://twitter.com/download/iphone" r...   
10    <a href="http://twitter.com/download/iphone" r...   
11    <a href="http://twitter.com/download/iphone" r...   
12    <a href="http://twitter.com/download/iphone" r...   
13    <a href="http://twitter.com/download/iphone" r...   
14    <a href="http://twitter.com/download/iphone" r...   
15    <a href="http://twitter.com/download/iphone" r...   
16    <a href="http://twitter.com/download/iphone" r...   
17    <a href="http://twitter.com/download/iphone" r...   
18    <a href="http://twitter.com/download/iphone" r...   
19    <a href="http://twitter.com/download/iphone" r...   
20    <a href="http://twitter.com/download/iphone" r...   
21    <a href="http://twitter.com/download/iphone" r...   
22    <a href="http://twitter.com/download/iphone" r...   
23    <a href="http://twitter.com/download/iphone" r...   
24    <a href="http://twitter.com/download/iphone" r...   
25    <a href="http://twitter.com/download/iphone" r...   
26    <a href="http://twitter.com/download/iphone" r...   
27    <a href="http://twitter.com/download/iphone" r...   
28    <a href="http://twitter.com/download/iphone" r...   
29    <a href="http://twitter.com/download/iphone" r...   
...                                                 ...   
2326  <a href="http://twitter.com/download/iphone" r...   
2327  <a href="http://twitter.com/download/iphone" r...   
2328  <a href="http://twitter.com/download/iphone" r...   
2329  <a href="http://twitter.com/download/iphone" r...   
2330  <a href="http://twitter.com/download/iphone" r...   
2331  <a href="http://twitter.com/download/iphone" r...   
2332  <a href="http://twitter.com/download/iphone" r...   
2333  <a href="http://twitter.com/download/iphone" r...   
2334  <a href="http://twitter.com/download/iphone" r...   
2335  <a href="http://twitter.com/download/iphone" r...   
2336  <a href="http://twitter.com/download/iphone" r...   
2337  <a href="http://twitter.com/download/iphone" r...   
2338  <a href="http://twitter.com/download/iphone" r...   
2339  <a href="http://twitter.com/download/iphone" r...   
2340  <a href="http://twitter.com/download/iphone" r...   
2341  <a href="http://twitter.com/download/iphone" r...   
2342  <a href="http://twitter.com/download/iphone" r...   
2343  <a href="http://twitter.com/download/iphone" r...   
2344  <a href="http://twitter.com/download/iphone" r...   
2345  <a href="http://twitter.com/download/iphone" r...   
2346  <a href="http://twitter.com/download/iphone" r...   
2347  <a href="http://twitter.com/download/iphone" r...   
2348  <a href="http://twitter.com/download/iphone" r...   
2349  <a href="http://twitter.com/download/iphone" r...   
2350  <a href="http://twitter.com/download/iphone" r...   
2351  <a href="http://twitter.com/download/iphone" r...   
2352  <a href="http://twitter.com/download/iphone" r...   
2353  <a href="http://twitter.com/download/iphone" r...   
2354  <a href="http://twitter.com/download/iphone" r...   
2355  <a href="http://twitter.com/download/iphone" r...   

                                                   text  retweeted_status_id  \
0     This is Phineas. He's a mystical boy. Only eve...                  NaN   
1     This is Tilly. She's just checking pup on you....                  NaN   
2     This is Archie. He is a rare Norwegian Pouncin...                  NaN   
3     This is Darla. She commenced a snooze mid meal...                  NaN   
4     This is Franklin. He would like you to stop ca...                  NaN   
5     Here we have a majestic great white breaching ...                  NaN   
6     Meet Jax. He enjoys ice cream so much he gets ...                  NaN   
7     When you watch your owner call another dog a g...                  NaN   
8     This is Zoey. She doesn't want to be one of th...                  NaN   
9     This is Cassie. She is a college pup. Studying...                  NaN   
10    This is Koda. He is a South Australian decksha...                  NaN   
11    This is Bruno. He is a service shark. Only get...                  NaN   
12    Here's a puppo that seems to be on the fence a...                  NaN   
13    This is Ted. He does his best. Sometimes that'...                  NaN   
14    This is Stuart. He's sporting his favorite fan...                  NaN   
15    This is Oliver. You're witnessing one of his m...                  NaN   
16    This is Jim. He found a fren. Taught him how t...                  NaN   
17    This is Zeke. He has a new stick. Very proud o...                  NaN   
18    This is Ralphus. He's powering up. Attempting ...                  NaN   
19    RT @dog_rates: This is Canela. She attempted s...         8.874740e+17   
20    This is Gerald. He was just told he didn't get...                  NaN   
21    This is Jeffrey. He has a monopoly on the pool...                  NaN   
22    I've yet to rate a Venezuelan Hover Wiener. Th...                  NaN   
23    This is Canela. She attempted some fancy porch...                  NaN   
24    You may not have known you needed to see this ...                  NaN   
25    This... is a Jubilant Antarctic House Bear. We...                  NaN   
26    This is Maya. She's very shy. Rarely leaves he...                  NaN   
27    This is Mingus. He's a wonderful father to his...                  NaN   
28    This is Derek. He's late for a dog meeting. 13...                  NaN   
29    This is Roscoe. Another pupper fallen victim t...                  NaN   
...                                                 ...                  ...   
2326  This is quite the dog. Gets really excited whe...                  NaN   
2327  This is a southern Vesuvius bumblegruff. Can d...                  NaN   
2328  Oh goodness. A super rare northeast Qdoba kang...                  NaN   
2329  Those are sunglasses and a jean jacket. 11/10 ...                  NaN   
2330  Unique dog here. Very small. Lives in containe...                  NaN   
2331  Here we have a mixed Asiago from the GalÃ¡pago...                  NaN   
2332  Look at this jokester thinking seat belt laws ...                  NaN   
2333  This is an extremely rare horned Parthenon. No...                  NaN   
2334  This is a funny dog. Weird toes. Won't come do...                  NaN   
2335  This is an Albanian 3 1/2 legged  Episcopalian...                  NaN   
2336     Can take selfies 11/10 https://t.co/ws2AMaNwPW                  NaN   
2337  Very concerned about fellow dog trapped in com...                  NaN   
2338  Not familiar with this breed. No tail (weird)....                  NaN   
2339  Oh my. Here you are seeing an Adobe Setter giv...                  NaN   
2340  Can stand on stump for what seems like a while...                  NaN   
2341  This appears to be a Mongolian Presbyterian mi...                  NaN   
2342  Here we have a well-established sunblockerspan...                  NaN   
2343  Let's hope this flight isn't Malaysian (lol). ...                  NaN   
2344  Here we have a northern speckled Rhododendron....                  NaN   
2345  This is the happiest dog you will ever see. Ve...                  NaN   
2346  Here is the Rand Paul of retrievers folks! He'...                  NaN   
2347  My oh my. This is a rare blond Canadian terrie...                  NaN   
2348  Here is a Siberian heavily armored polar bear ...                  NaN   
2349  This is an odd dog. Hard on the outside but lo...                  NaN   
2350  This is a truly beautiful English Wilson Staff...                  NaN   
2351  Here we have a 1949 1st generation vulpix. Enj...                  NaN   
2352  This is a purebred Piers Morgan. Loves to Netf...                  NaN   
2353  Here is a very happy pup. Big fan of well-main...                  NaN   
2354  This is a western brown Mitsubishi terrier. Up...                  NaN   
2355  Here we have a Japanese Irish Setter. Lost eye...                  NaN   

      retweeted_status_user_id retweeted_status_timestamp  \
0                          NaN                        NaN   
1                          NaN                        NaN   
2                          NaN                        NaN   
3                          NaN                        NaN   
4                          NaN                        NaN   
5                          NaN                        NaN   
6                          NaN                        NaN   
7                          NaN                        NaN   
8                          NaN                        NaN   
9                          NaN                        NaN   
10                         NaN                        NaN   
11                         NaN                        NaN   
12                         NaN                        NaN   
13                         NaN                        NaN   
14                         NaN                        NaN   
15                         NaN                        NaN   
16                         NaN                        NaN   
17                         NaN                        NaN   
18                         NaN                        NaN   
19                4.196984e+09  2017-07-19 00:47:34 +0000   
20                         NaN                        NaN   
21                         NaN                        NaN   
22                         NaN                        NaN   
23                         NaN                        NaN   
24                         NaN                        NaN   
25                         NaN                        NaN   
26                         NaN                        NaN   
27                         NaN                        NaN   
28                         NaN                        NaN   
29                         NaN                        NaN   
...                        ...                        ...   
2326                       NaN                        NaN   
2327                       NaN                        NaN   
2328                       NaN                        NaN   
2329                       NaN                        NaN   
2330                       NaN                        NaN   
2331                       NaN                        NaN   
2332                       NaN                        NaN   
2333                       NaN                        NaN   
2334                       NaN                        NaN   
2335                       NaN                        NaN   
2336                       NaN                        NaN   
2337                       NaN                        NaN   
2338                       NaN                        NaN   
2339                       NaN                        NaN   
2340                       NaN                        NaN   
2341                       NaN                        NaN   
2342                       NaN                        NaN   
2343                       NaN                        NaN   
2344                       NaN                        NaN   
2345                       NaN                        NaN   
2346                       NaN                        NaN   
2347                       NaN                        NaN   
2348                       NaN                        NaN   
2349                       NaN                        NaN   
2350                       NaN                        NaN   
2351                       NaN                        NaN   
2352                       NaN                        NaN   
2353                       NaN                        NaN   
2354                       NaN                        NaN   
2355                       NaN                        NaN   

                                          expanded_urls  rating_numerator  \
0     https://twitter.com/dog_rates/status/892420643...                13   
1     https://twitter.com/dog_rates/status/892177421...                13   
2     https://twitter.com/dog_rates/status/891815181...                12   
3     https://twitter.com/dog_rates/status/891689557...                13   
4     https://twitter.com/dog_rates/status/891327558...                12   
5     https://twitter.com/dog_rates/status/891087950...                13   
6     https://gofundme.com/ydvmve-surgery-for-jax,ht...                13   
7     https://twitter.com/dog_rates/status/890729181...                13   
8     https://twitter.com/dog_rates/status/890609185...                13   
9     https://twitter.com/dog_rates/status/890240255...                14   
10    https://twitter.com/dog_rates/status/890006608...                13   
11    https://twitter.com/dog_rates/status/889880896...                13   
12    https://twitter.com/dog_rates/status/889665388...                13   
13    https://twitter.com/dog_rates/status/889638837...                12   
14    https://twitter.com/dog_rates/status/889531135...                13   
15    https://twitter.com/dog_rates/status/889278841...                13   
16    https://twitter.com/dog_rates/status/888917238...                12   
17    https://twitter.com/dog_rates/status/888804989...                13   
18    https://twitter.com/dog_rates/status/888554962...                13   
19    https://twitter.com/dog_rates/status/887473957...                13   
20    https://twitter.com/dog_rates/status/888078434...                12   
21    https://twitter.com/dog_rates/status/887705289...                13   
22    https://twitter.com/dog_rates/status/887517139...                14   
23    https://twitter.com/dog_rates/status/887473957...                13   
24    https://twitter.com/dog_rates/status/887343217...                13   
25    https://twitter.com/dog_rates/status/887101392...                12   
26    https://twitter.com/dog_rates/status/886983233...                13   
27    https://www.gofundme.com/mingusneedsus,https:/...                13   
28    https://twitter.com/dog_rates/status/886680336...                13   
29    https://twitter.com/dog_rates/status/886366144...                12   
...                                                 ...               ...   
2326  https://twitter.com/dog_rates/status/666411507...                 2   
2327  https://twitter.com/dog_rates/status/666407126...                 7   
2328  https://twitter.com/dog_rates/status/666396247...                 9   
2329  https://twitter.com/dog_rates/status/666373753...                11   
2330  https://twitter.com/dog_rates/status/666362758...                 6   
2331  https://twitter.com/dog_rates/status/666353288...                 8   
2332  https://twitter.com/dog_rates/status/666345417...                10   
2333  https://twitter.com/dog_rates/status/666337882...                 9   
2334  https://twitter.com/dog_rates/status/666293911...                 3   
2335  https://twitter.com/dog_rates/status/666287406...                 1   
2336  https://twitter.com/dog_rates/status/666273097...                11   
2337  https://twitter.com/dog_rates/status/666268910...                10   
2338  https://twitter.com/dog_rates/status/666104133...                 1   
2339  https://twitter.com/dog_rates/status/666102155...                11   
2340  https://twitter.com/dog_rates/status/666099513...                 8   
2341  https://twitter.com/dog_rates/status/666094000...                 9   
2342  https://twitter.com/dog_rates/status/666082916...                 6   
2343  https://twitter.com/dog_rates/status/666073100...                10   
2344  https://twitter.com/dog_rates/status/666071193...                 9   
2345  https://twitter.com/dog_rates/status/666063827...                10   
2346  https://twitter.com/dog_rates/status/666058600...                 8   
2347  https://twitter.com/dog_rates/status/666057090...                 9   
2348  https://twitter.com/dog_rates/status/666055525...                10   
2349  https://twitter.com/dog_rates/status/666051853...                 2   
2350  https://twitter.com/dog_rates/status/666050758...                10   
2351  https://twitter.com/dog_rates/status/666049248...                 5   
2352  https://twitter.com/dog_rates/status/666044226...                 6   
2353  https://twitter.com/dog_rates/status/666033412...                 9   
2354  https://twitter.com/dog_rates/status/666029285...                 7   
2355  https://twitter.com/dog_rates/status/666020888...                 8   

      rating_denominator      name  doggo floofer  pupper  puppo  
0                     10   Phineas   None    None    None   None  
1                     10     Tilly   None    None    None   None  
2                     10    Archie   None    None    None   None  
3                     10     Darla   None    None    None   None  
4                     10  Franklin   None    None    None   None  
5                     10      None   None    None    None   None  
6                     10       Jax   None    None    None   None  
7                     10      None   None    None    None   None  
8                     10      Zoey   None    None    None   None  
9                     10    Cassie  doggo    None    None   None  
10                    10      Koda   None    None    None   None  
11                    10     Bruno   None    None    None   None  
12                    10      None   None    None    None  puppo  
13                    10       Ted   None    None    None   None  
14                    10    Stuart   None    None    None  puppo  
15                    10    Oliver   None    None    None   None  
16                    10       Jim   None    None    None   None  
17                    10      Zeke   None    None    None   None  
18                    10   Ralphus   None    None    None   None  
19                    10    Canela   None    None    None   None  
20                    10    Gerald   None    None    None   None  
21                    10   Jeffrey   None    None    None   None  
22                    10      such   None    None    None   None  
23                    10    Canela   None    None    None   None  
24                    10      None   None    None    None   None  
25                    10      None   None    None    None   None  
26                    10      Maya   None    None    None   None  
27                    10    Mingus   None    None    None   None  
28                    10     Derek   None    None    None   None  
29                    10    Roscoe   None    None  pupper   None  
...                  ...       ...    ...     ...     ...    ...  
2326                  10     quite   None    None    None   None  
2327                  10         a   None    None    None   None  
2328                  10      None   None    None    None   None  
2329                  10      None   None    None    None   None  
2330                  10      None   None    None    None   None  
2331                  10      None   None    None    None   None  
2332                  10      None   None    None    None   None  
2333                  10        an   None    None    None   None  
2334                  10         a   None    None    None   None  
2335                   2        an   None    None    None   None  
2336                  10      None   None    None    None   None  
2337                  10      None   None    None    None   None  
2338                  10      None   None    None    None   None  
2339                  10      None   None    None    None   None  
2340                  10      None   None    None    None   None  
2341                  10      None   None    None    None   None  
2342                  10      None   None    None    None   None  
2343                  10      None   None    None    None   None  
2344                  10      None   None    None    None   None  
2345                  10       the   None    None    None   None  
2346                  10       the   None    None    None   None  
2347                  10         a   None    None    None   None  
2348                  10         a   None    None    None   None  
2349                  10        an   None    None    None   None  
2350                  10         a   None    None    None   None  
2351                  10      None   None    None    None   None  
2352                  10         a   None    None    None   None  
2353                  10         a   None    None    None   None  
2354                  10         a   None    None    None   None  
2355                  10      None   None    None    None   None  

[2356 rows x 17 columns]>

dog['rating_numerator']

0       13
1       13
2       12
3       13
4       12
5       13
6       13
7       13
8       13
9       14
10      13
11      13
12      13
13      12
14      13
15      13
16      12
17      13
18      13
19      13
20      12
21      13
22      14
23      13
24      13
25      12
26      13
27      13
28      13
29      12
        ..
2326     2
2327     7
2328     9
2329    11
2330     6
2331     8
2332    10
2333     9
2334     3
2335     1
2336    11
2337    10
2338     1
2339    11
2340     8
2341     9
2342     6
2343    10
2344     9
2345    10
2346     8
2347     9
2348    10
2349     2
2350    10
2351     5
2352     6
2353     9
2354     7
2355     8
Name: rating_numerator, Length: 2356, dtype: int64

This file (image_predictions.tsv) is hosted on Udacity's servers and should be downloaded programmatically using the Requests library and the following URL

import requests

url = 'https://d17h27t6h515a5.cloudfront.net/topher/2017/August/599fd2ad_image-predictions/image-predictions.tsv'
response = requests.get(url)

with open(url.split('/')[-1], mode='wb') as file:
    file.write(response.content)
    
dog_images = pd.read_csv('image-predictions.tsv', sep='\t')
dog_images.head(10)

Each tweet's retweet count and favorite ("like") count at minimum, and any additional data you find interesting. Using the tweet IDs in the WeRateDogs Twitter archive, query the Twitter API for each tweet's JSON data using Python's Tweepy library and store each tweet's entire set of JSON data in a file called tweet_json.txt file. Each tweet's JSON data should be written to its own line. Then read this .txt file line by line into a pandas DataFrame with (at minimum) tweet ID, retweet count, and favorite count. Note: do not include your Twitter API keys, secrets, and tokens in your project submission.

import tweepy


consumer_key = '4ckFbeGhC4HgeHwrhIUBOpfx4'
consumer_secret = 'ZpIhhcQoTFqtTnYmsgAZFWExsdgl0FaHqlF4p5OhhXr97gJjX0'
access_token = '775482130520543232-Bf2EQ0TEdx4hFYBQD8Nk5mriXEKQxwZ'
access_secret = 'cdGASZpGVf3AHl6sP3tOqz9Uwj0AxE31oQerlJN0yI50O'

auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_secret)

api = tweepy.API(auth)
api.wait_on_rate_limit = True
api.wait_on_rate_limit_notify = True

Tweet data is stored in JSON format by Twitter. Getting tweet JSON data via tweet ID using Tweepy is described well in this StackOverflow answer. Note that setting the tweet_mode parameter to 'extended' in the get_status call, i.e., api.get_status(tweet_id, tweet_mode='extended'), can be useful.

# # Creat a list where we will store the result
# df_list = []
# #where we will store the tweet_id of the errors
# error_list = []

# tweet_id = dog_images['tweet_id']
# for id in tweet_id:
#     try:
    
#         page = api.get_status(id)
#         favorites = page['favorite_count'] # How many favorites the tweet had
#         retweets = page['retweet_count'] # Count of the retweet
#         date_time = page['created_at'] # The date and time of the creation
        
#         df_list.append({'tweet_id': int(id),
#                         'favorites': int(favorites),
#                         'retweets': int(retweets),
#                         'date_time': pd.to_datetime(date_time)})
    
    
#     # Catch the exceptions of the TweepError
#     except Exception as e:
#         print(str(tweet_id)+ " _ " + str(e))
#         error_list.append(id)

# # lengh of the result
# print(len(df_list))
# # The tweet_id of the errors
# print(len(error_list))

with open('tweet_json.txt', 'w') as file:
    for tweet_id in dog['tweet_id']:

        try:

            status = api.get_status(tweet_id)

            json.dump(status._json, file)

            file.write('\n')

        except:

            print("missing ", tweet_id)

missing  888202515573088257
missing  873697596434513921
missing  869988702071779329
missing  866816280283807744
missing  861769973181624320
missing  842892208864923648
missing  802247111496568832
missing  775096608509886464
Rate limit reached. Sleeping for: 705
Rate limit reached. Sleeping for: 707

import json
twt_id = []
faves = []
rts = []

with open('tweet_json.txt',mode='r')as json_file:
    for line in json_file.readlines():
        tweet_data = json.loads(line)
        twt_id.append(tweet_data['id'])
        faves.append(tweet_data['favorite_count'])
        rts.append(tweet_data['retweet_count'])
        
additional_tweet_data = pd.DataFrame({'tweet_id':twt_id, 'favorite_count':faves, 'retweet_count':rts})

additional_tweet_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2348 entries, 0 to 2347
Data columns (total 3 columns):
favorite_count    2348 non-null int64
retweet_count     2348 non-null int64
tweet_id          2348 non-null int64
dtypes: int64(3)
memory usage: 55.1 KB

dog.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2356 entries, 0 to 2355
Data columns (total 17 columns):
tweet_id                      2356 non-null int64
in_reply_to_status_id         78 non-null float64
in_reply_to_user_id           78 non-null float64
timestamp                     2356 non-null object
source                        2356 non-null object
text                          2356 non-null object
retweeted_status_id           181 non-null float64
retweeted_status_user_id      181 non-null float64
retweeted_status_timestamp    181 non-null object
expanded_urls                 2297 non-null object
rating_numerator              2356 non-null int64
rating_denominator            2356 non-null int64
name                          2356 non-null object
doggo                         2356 non-null object
floofer                       2356 non-null object
pupper                        2356 non-null object
puppo                         2356 non-null object
dtypes: float64(4), int64(3), object(10)
memory usage: 313.0+ KB

dog_images.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2075 entries, 0 to 2074
Data columns (total 12 columns):
tweet_id    2075 non-null int64
jpg_url     2075 non-null object
img_num     2075 non-null int64
p1          2075 non-null object
p1_conf     2075 non-null float64
p1_dog      2075 non-null bool
p2          2075 non-null object
p2_conf     2075 non-null float64
p2_dog      2075 non-null bool
p3          2075 non-null object
p3_conf     2075 non-null float64
p3_dog      2075 non-null bool
dtypes: bool(3), float64(3), int64(2), object(4)
memory usage: 152.1+ KB

ACCESSING DATA¶

dog.describe()

dog.sample(7)

dog.rating_numerator.value_counts()

12      558
11      464
10      461
13      351
9       158
8       102
7        55
14       54
5        37
6        32
3        19
4        17
1         9
2         9
420       2
0         2
15        2
75        2
80        1
20        1
24        1
26        1
44        1
50        1
60        1
165       1
84        1
88        1
144       1
182       1
143       1
666       1
960       1
1776      1
17        1
27        1
45        1
99        1
121       1
204       1
Name: rating_numerator, dtype: int64

print(dog[dog.tweet_id.isnull()])
print(dog[dog.tweet_id.duplicated()])

Empty DataFrame
Columns: [tweet_id, in_reply_to_status_id, in_reply_to_user_id, timestamp, source, text, retweeted_status_id, retweeted_status_user_id, retweeted_status_timestamp, expanded_urls, rating_numerator, rating_denominator, name, doggo, floofer, pupper, puppo]
Index: []
Empty DataFrame
Columns: [tweet_id, in_reply_to_status_id, in_reply_to_user_id, timestamp, source, text, retweeted_status_id, retweeted_status_user_id, retweeted_status_timestamp, expanded_urls, rating_numerator, rating_denominator, name, doggo, floofer, pupper, puppo]
Index: []

print(dog[dog.rating_numerator == 0])

                tweet_id  in_reply_to_status_id  in_reply_to_user_id  \
315   835152434251116546                    NaN                  NaN   
1016  746906459439529985           7.468859e+17         4.196984e+09   

                      timestamp  \
315   2017-02-24 15:40:31 +0000   
1016  2016-06-26 03:22:31 +0000   

                                                 source  \
315   <a href="http://twitter.com/download/iphone" r...   
1016  <a href="http://twitter.com/download/iphone" r...   

                                                   text  retweeted_status_id  \
315   When you're so blinded by your systematic plag...                  NaN   
1016  PUPDATE: can't see any. Even if I could, I cou...                  NaN   

      retweeted_status_user_id retweeted_status_timestamp  \
315                        NaN                        NaN   
1016                       NaN                        NaN   

                                          expanded_urls  rating_numerator  \
315   https://twitter.com/dog_rates/status/835152434...                 0   
1016  https://twitter.com/dog_rates/status/746906459...                 0   

      rating_denominator  name doggo floofer pupper puppo  
315                   10  None  None    None   None  None  
1016                  10  None  None    None   None  None

print(dog.name.value_counts())

None        745
a            55
Charlie      12
Cooper       11
Lucy         11
Oliver       11
Lola         10
Penny        10
Tucker       10
Winston       9
Bo            9
Sadie         8
the           8
Toby          7
Buddy         7
Bailey        7
an            7
Daisy         7
Rusty         6
Oscar         6
Dave          6
Bella         6
Koda          6
Scout         6
Jack          6
Jax           6
Stanley       6
Leo           6
Milo          6
Gus           5
           ... 
Maya          1
Walker        1
Huck          1
old           1
Travis        1
Sprout        1
Al            1
Striker       1
Tycho         1
Shelby        1
Ole           1
Barclay       1
Ron           1
Sandra        1
Bode          1
Bobble        1
Vinscent      1
Rooney        1
Karl          1
Ivar          1
Poppy         1
Stormy        1
Marq          1
Winifred      1
Major         1
Toffee        1
Eevee         1
Zeek          1
Maude         1
Timber        1
Name: name, Length: 957, dtype: int64

dog_images.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2075 entries, 0 to 2074
Data columns (total 12 columns):
tweet_id    2075 non-null int64
jpg_url     2075 non-null object
img_num     2075 non-null int64
p1          2075 non-null object
p1_conf     2075 non-null float64
p1_dog      2075 non-null bool
p2          2075 non-null object
p2_conf     2075 non-null float64
p2_dog      2075 non-null bool
p3          2075 non-null object
p3_conf     2075 non-null float64
p3_dog      2075 non-null bool
dtypes: bool(3), float64(3), int64(2), object(4)
memory usage: 152.1+ KB

dog_images.describe()

additional_tweet_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2348 entries, 0 to 2347
Data columns (total 3 columns):
favorite_count    2348 non-null int64
retweet_count     2348 non-null int64
tweet_id          2348 non-null int64
dtypes: int64(3)
memory usage: 55.1 KB

additional_tweet_data.describe()

Tidiness Issues¶

1,doggo,floofer,pupper,puppo should be within a column called "name" 2,combine three dataframe as one dataframe, then drop the unnecessary column

quality issues¶

1 dog dataframe wrong data type: tweet_id:int64( should be string) in_reply_to_status_id:float64(should be string) in_reply_to_user_id:float64(should be string) retweeted_status_id:float64 retweeted_status_user_id:float64 (should be string) timestamp:object(should be Datetime)

2 dog_images dataframe wrong data type: tweet_id:int64 (SHOULD BE STRING)

3 additional_tweet_data dataframe, wrong data type: tweet_id:int64 (SHOULD BE STRING)

4 745 dogs no names,55 dogs named a None 745 a 55

5 two dogs' rating is 0 tweet_id
315 835152434251116546
1016 746906459439529985

Cleaning Data¶

#creating copies of the dataframes to clean. 
dog_clean = dog.copy()
additional_tweet_data_clean = additional_tweet_data.copy()
dog_images_clean = dog_images.copy()

Melt the doggo, pupper, puppo, and floofer columns into one column¶

# dog_clean.tweet_id
tweet_ids = dog_clean.tweet_id.tolist()
tweet_ids

[892420643555336193,
 892177421306343426,
 891815181378084864,
 891689557279858688,
 891327558926688256,
 891087950875897856,
 890971913173991426,
 890729181411237888,
 890609185150312448,
 890240255349198849,
 890006608113172480,
 889880896479866881,
 889665388333682689,
 889638837579907072,
 889531135344209921,
 889278841981685760,
 888917238123831296,
 888804989199671297,
 888554962724278272,
 888202515573088257,
 888078434458587136,
 887705289381826560,
 887517139158093824,
 887473957103951883,
 887343217045368832,
 887101392804085760,
 886983233522544640,
 886736880519319552,
 886680336477933568,
 886366144734445568,
 886267009285017600,
 886258384151887873,
 886054160059072513,
 885984800019947520,
 885528943205470208,
 885518971528720385,
 885311592912609280,
 885167619883638784,
 884925521741709313,
 884876753390489601,
 884562892145688576,
 884441805382717440,
 884247878851493888,
 884162670584377345,
 883838122936631299,
 883482846933004288,
 883360690899218434,
 883117836046086144,
 882992080364220416,
 882762694511734784,
 882627270321602560,
 882268110199369728,
 882045870035918850,
 881906580714921986,
 881666595344535552,
 881633300179243008,
 881536004380872706,
 881268444196462592,
 880935762899988482,
 880872448815771648,
 880465832366813184,
 880221127280381952,
 880095782870896641,
 879862464715927552,
 879674319642796034,
 879492040517615616,
 879415818425184262,
 879376492567855104,
 879130579576475649,
 879050749262655488,
 879008229531029506,
 878776093423087618,
 878604707211726852,
 878404777348136964,
 878316110768087041,
 878281511006478336,
 878057613040115712,
 877736472329191424,
 877611172832227328,
 877556246731214848,
 877316821321428993,
 877201837425926144,
 876838120628539392,
 876537666061221889,
 876484053909872640,
 876120275196170240,
 875747767867523072,
 875144289856114688,
 875097192612077568,
 875021211251597312,
 874680097055178752,
 874434818259525634,
 874296783580663808,
 874057562936811520,
 874012996292530176,
 873697596434513921,
 873580283840344065,
 873337748698140672,
 873213775632977920,
 872967104147763200,
 872820683541237760,
 872668790621863937,
 872620804844003328,
 872486979161796608,
 872261713294495745,
 872122724285648897,
 871879754684805121,
 871762521631449091,
 871515927908634625,
 871166179821445120,
 871102520638267392,
 871032628920680449,
 870804317367881728,
 870726314365509632,
 870656317836468226,
 870374049280663552,
 870308999962521604,
 870063196459192321,
 869988702071779329,
 869772420881756160,
 869702957897576449,
 869596645499047938,
 869227993411051520,
 868880397819494401,
 868639477480148993,
 868622495443632128,
 868552278524837888,
 867900495410671616,
 867774946302451713,
 867421006826221569,
 867072653475098625,
 867051520902168576,
 866816280283807744,
 866720684873056260,
 866686824827068416,
 866450705531457537,
 866334964761202691,
 866094527597207552,
 865718153858494464,
 865359393868664832,
 865006731092295680,
 864873206498414592,
 864279568663928832,
 864197398364647424,
 863907417377173506,
 863553081350529029,
 863471782782697472,
 863432100342583297,
 863427515083354112,
 863079547188785154,
 863062471531167744,
 862831371563274240,
 862722525377298433,
 862457590147678208,
 862096992088072192,
 861769973181624320,
 861383897657036800,
 861288531465048066,
 861005113778896900,
 860981674716409858,
 860924035999428608,
 860563773140209665,
 860524505164394496,
 860276583193509888,
 860184849394610176,
 860177593139703809,
 859924526012018688,
 859851578198683649,
 859607811541651456,
 859196978902773760,
 859074603037188101,
 858860390427611136,
 858843525470990336,
 858471635011153920,
 858107933456039936,
 857989990357356544,
 857746408056729600,
 857393404942143489,
 857263160327368704,
 857214891891077121,
 857062103051644929,
 857029823797047296,
 856602993587888130,
 856543823941562368,
 856526610513747968,
 856330835276025856,
 856288084350160898,
 856282028240666624,
 855862651834028034,
 855860136149123072,
 855857698524602368,
 855851453814013952,
 855818117272018944,
 855459453768019968,
 855245323840757760,
 855138241867124737,
 854732716440526848,
 854482394044301312,
 854365224396361728,
 854120357044912130,
 854010172552949760,
 853760880890318849,
 853639147608842240,
 853299958564483072,
 852936405516943360,
 852912242202992640,
 852672615818899456,
 852553447878664193,
 852311364735569921,
 852226086759018497,
 852189679701164033,
 851953902622658560,
 851861385021730816,
 851591660324737024,
 851464819735769094,
 851224888060895234,
 850753642995093505,
 850380195714523136,
 850333567704068097,
 850145622816686080,
 850019790995546112,
 849776966551130114,
 849668094696017920,
 849412302885593088,
 849336543269576704,
 849051919805034497,
 848690551926992896,
 848324959059550208,
 848213670039564288,
 848212111729840128,
 847978865427394560,
 847971574464610304,
 847962785489326080,
 847842811428974592,
 847617282490613760,
 847606175596138505,
 847251039262605312,
 847157206088847362,
 847116187444137987,
 846874817362120707,
 846514051647705089,
 846505985330044928,
 846153765933735936,
 846139713627017216,
 846042936437604353,
 845812042753855489,
 845677943972139009,
 845459076796616705,
 845397057150107648,
 845306882940190720,
 845098359547420673,
 844979544864018432,
 844973813909606400,
 844704788403113984,
 844580511645339650,
 844223788422217728,
 843981021012017153,
 843856843873095681,
 843604394117681152,
 843235543001513987,
 842892208864923648,
 842846295480000512,
 842765311967449089,
 842535590457499648,
 842163532590374912,
 842115215311396866,
 841833993020538882,
 841680585030541313,
 841439858740625411,
 841320156043304961,
 841314665196081154,
 841077006473256960,
 840761248237133825,
 840728873075638272,
 840698636975636481,
 840696689258311684,
 840632337062862849,
 840370681858686976,
 840268004936019968,
 839990271299457024,
 839549326359670784,
 839290600511926273,
 839239871831150596,
 838952994649550848,
 838921590096166913,
 838916489579200512,
 838831947270979586,
 838561493054533637,
 838476387338051585,
 838201503651401729,
 838150277551247360,
 838085839343206401,
 838083903487373313,
 837820167694528512,
 837482249356513284,
 837471256429613056,
 837366284874571778,
 837110210464448512,
 837012587749474308,
 836989968035819520,
 836753516572119041,
 836677758902222849,
 836648853927522308,
 836397794269200385,
 836380477523124226,
 836260088725786625,
 836001077879255040,
 835685285446955009,
 835574547218894849,
 835536468978302976,
 835309094223372289,
 835297930240217089,
 835264098648616962,
 835246439529840640,
 835172783151792128,
 835152434251116546,
 834931633769889797,
 834786237630337024,
 834574053763584002,
 834477809192075265,
 834458053273591808,
 834209720923721728,
 834167344700198914,
 834089966724603904,
 834086379323871233,
 833863086058651648,
 833826103416520705,
 833732339549220864,
 833722901757046785,
 833479644947025920,
 833124694597443584,
 832998151111966721,
 832769181346996225,
 832757312314028032,
 832682457690300417,
 832645525019123713,
 832636094638288896,
 832397543355072512,
 832369877331693569,
 832273440279240704,
 832215909146226688,
 832215726631055365,
 832088576586297345,
 832040443403784192,
 832032802820481025,
 831939777352105988,
 831926988323639298,
 831911600680497154,
 831670449226514432,
 831650051525054464,
 831552930092285952,
 831322785565769729,
 831315979191906304,
 831309418084069378,
 831262627380748289,
 830956169170665475,
 830583320585068544,
 830173239259324417,
 830097400375152640,
 829878982036299777,
 829861396166877184,
 829501995190984704,
 829449946868879360,
 829374341691346946,
 829141528400556032,
 829011960981237760,
 828801551087042563,
 828770345708580865,
 828708714936930305,
 828650029636317184,
 828409743546925057,
 828408677031882754,
 828381636999917570,
 828376505180889089,
 828372645993398273,
 828361771580813312,
 828046555563323392,
 828011680017821696,
 827933404142436356,
 827653905312006145,
 827600520311402496,
 827324948884643840,
 827228250799742977,
 827199976799354881,
 826958653328592898,
 826848821049180160,
 826615380357632002,
 826598799820865537,
 826598365270007810,
 826476773533745153,
 826240494070030336,
 826204788643753985,
 826115272272650244,
 825876512159186944,
 825829644528148480,
 825535076884762624,
 825147591692263424,
 825120256414846976,
 825026590719483904,
 824796380199809024,
 824775126675836928,
 824663926340194305,
 824325613288833024,
 824297048279236611,
 824025158776213504,
 823939628516474880,
 823719002937630720,
 823699002998870016,
 823581115634085888,
 823333489516937216,
 823322678127919110,
 823269594223824897,
 822975315408461824,
 822872901745569793,
 822859134160621569,
 822647212903690241,
 822610361945911296,
 822489057087389700,
 822462944365645825,
 822244816520155136,
 822163064745328640,
 821886076407029760,
 821813639212650496,
 821765923262631936,
 821522889702862852,
 821421320206483457,
 821407182352777218,
 821153421864615936,
 821149554670182400,
 821107785811234820,
 821044531881721856,
 820837357901512704,
 820749716845686786,
 820690176645140481,
 820494788566847489,
 820446719150292993,
 820314633777061888,
 820078625395449857,
 820013781606658049,
 819952236453363712,
 819924195358416896,
 819711362133872643,
 819588359383371776,
 819347104292290561,
 819238181065359361,
 819227688460238848,
 819015337530290176,
 819015331746349057,
 819006400881917954,
 819004803107983360,
 818646164899774465,
 818627210458333184,
 818614493328580609,
 818588835076603904,
 818536468981415936,
 818307523543449600,
 818259473185828864,
 818145370475810820,
 817908911860748288,
 817827839487737858,
 817777686764523521,
 817536400337801217,
 817502432452313088,
 817423860136083457,
 817415592588222464,
 817181837579653120,
 817171292965273600,
 817120970343411712,
 817056546584727552,
 816829038950027264,
 816816676327063552,
 816697700272001025,
 816450570814898180,
 816336735214911488,
 816091915477250048,
 816062466425819140,
 816014286006976512,
 815990720817401858,
 815966073409433600,
 815745968457060357,
 815736392542261248,
 815639385530101762,
 815390420867969024,
 814986499976527872,
 814638523311648768,
 814578408554463233,
 814530161257443328,
 814153002265309185,
 813944609378369540,
 813910438903693312,
 813812741911748608,
 813800681631023104,
 813217897535406080,
 813202720496779264,
 813187593374461952,
 813172488309972993,
 813157409116065792,
 813142292504645637,
 813130366689148928,
 813127251579564032,
 813112105746448384,
 813096984823349248,
 813081950185472002,
 813066809284972545,
 813051746834595840,
 812781120811126785,
 812747805718642688,
 812709060537683968,
 812503143955202048,
 812466873996607488,
 812372279581671427,
 811985624773361665,
 811744202451197953,
 811647686436880384,
 811627233043480576,
 811386762094317568,
 810984652412424192,
 810896069567610880,
 810657578271330305,
 810284430598270976,
 810254108431155201,
 809920764300447744,
 809808892968534016,
 809448704142938112,
 809220051211603969,
 809084759137812480,
 808838249661788160,
 808733504066486276,
 808501579447930884,
 808344865868283904,
 808134635716833280,
 808106460588765185,
 808001312164028416,
 807621403335917568,
 807106840509214720,
 807059379405148160,
 807010152071229440,
 806629075125202948,
 806620845233815552,
 806576416489959424,
 806542213899489280,
 806242860592926720,
 806219024703037440,
 805958939288408065,
 805932879469572096,
 805826884734976000,
 805823200554876929,
 805520635690676224,
 805487436403003392,
 805207613751304193,
 804738756058218496,
 804475857670639616,
 804413760345620481,
 804026241225523202,
 803773340896923648,
 803692223237865472,
 803638050916102144,
 803380650405482500,
 803321560782307329,
 803276597545603072,
 802952499103731712,
 802624713319034886,
 802600418706604034,
 802572683846291456,
 802323869084381190,
 802265048156610565,
 802247111496568832,
 802239329049477120,
 802185808107208704,
 801958328846974976,
 801854953262350336,
 801538201127157760,
 801285448605831168,
 801167903437357056,
 801127390143516673,
 801115127852503040,
 800859414831898624,
 800855607700029440,
 800751577355128832,
 800513324630806528,
 800459316964663297,
 800443802682937345,
 800388270626521089,
 800188575492947969,
 800141422401830912,
 800018252395122689,
 799774291445383169,
 799757965289017345,
 799422933579902976,
 799308762079035393,
 799297110730567681,
 799063482566066176,
 798933969379225600,
 798925684722855936,
 798705661114773508,
 798701998996647937,
 798697898615730177,
 798694562394996736,
 798686750113755136,
 798682547630837760,
 798673117451325440,
 798665375516884993,
 798644042770751489,
 798628517273620480,
 798585098161549313,
 798576900688019456,
 798340744599797760,
 798209839306514432,
 797971864723324932,
 797545162159308800,
 797236660651966464,
 797165961484890113,
 796904159865868288,
 796865951799083009,
 796759840936919040,
 796563435802726400,
 796484825502875648,
 796387464403357696,
 796177847564038144,
 796149749086875649,
 796125600683540480,
 796116448414461957,
 796080075804475393,
 796031486298386433,
 795464331001561088,
 795400264262053889,
 795076730285391872,
 794983741416415232,
 794926597468000259,
 794355576146903043,
 794332329137291264,
 794205286408003585,
 793962221541933056,
 793845145112371200,
 793614319594401792,
 793601777308463104,
 793500921481273345,
 793286476301799424,
 793271401113350145,
 793256262322548741,
 793241302385262592,
 793226087023144960,
 793210959003287553,
 793195938047070209,
 793180763617361921,
 793165685325201412,
 793150605191548928,
 793135492858580992,
 793120401413079041,
 792913359805018113,
 792883833364439040,
 792773781206999040,
 792394556390137856,
 792050063153438720,
 791821351946420224,
 791784077045166082,
 791780927877898241,
 791774931465953280,
 791672322847637504,
 791406955684368384,
 791312159183634433,
 791026214425268224,
 790987426131050500,
 790946055508652032,
 790723298204217344,
 790698755171364864,
 790581949425475584,
 790337589677002753,
 790277117346975746,
 790227638568808452,
 789986466051088384,
 789960241177853952,
 789903600034189313,
 789628658055020548,
 789599242079838210,
 789530877013393408,
 789314372632018944,
 789280767834746880,
 789268448748703744,
 789137962068021249,
 788908386943430656,
 788765914992902144,
 788552643979468800,
 788412144018661376,
 788178268662984705,
 788150585577050112,
 788070120937619456,
 788039637453406209,
 787810552592695296,
 787717603741622272,
 787397959788929025,
 787322443945877504,
 787111942498508800,
 786963064373534720,
 786729988674449408,
 786709082849828864,
 786664955043049472,
 786595970293370880,
 786363235746385920,
 786286427768250368,
 786233965241827333,
 786051337297522688,
 786036967502913536,
 785927819176054784,
 785872687017132033,
 785639753186217984,
 785533386513321988,
 785515384317313025,
 785264754247995392,
 785170936622350336,
 784826020293709826,
 784517518371221505,
 784431430411685888,
 784183165795655680,
 784057939640352768,
 783839966405230592,
 783821107061198850,
 783695101801398276,
 783466772167098368,
 783391753726550016,
 783347506784731136,
 783334639985389568,
 783085703974514689,
 782969140009107456,
 782747134529531904,
 782722598790725632,
 782598640137187329,
 782305867769217024,
 782021823840026624,
 781955203444699136,
 781661882474196992,
 781655249211752448,
 781524693396357120,
 781308096455073793,
 781251288990355457,
 781163403222056960,
 780931614150983680,
 780858289093574656,
 780800785462489090,
 780601303617732608,
 780543529827336192,
 780496263422808064,
 780476555013349377,
 780459368902959104,
 780192070812196864,
 780092040432480260,
 780074436359819264,
 779834332596887552,
 779377524342161408,
 779124354206535695,
 779123168116150273,
 779056095788752897,
 778990705243029504,
 778774459159379968,
 778764940568104960,
 778748913645780993,
 778650543019483137,
 778624900596654080,
 778408200802557953,
 778396591732486144,
 778383385161035776,
 778286810187399168,
 778039087836069888,
 778027034220126208,
 777953400541634568,
 777885040357281792,
 777684233540206592,
 777641927919427584,
 777621514455814149,
 777189768882946048,
 776819012571455488,
 776813020089548800,
 776477788987613185,
 776249906839351296,
 776218204058357768,
 776201521193218049,
 776113305656188928,
 776088319444877312,
 775898661951791106,
 775842724423557120,
 775733305207554048,
 775729183532220416,
 775364825476165632,
 775350846108426240,
 775096608509886464,
 775085132600442880,
 774757898236878852,
 774639387460112384,
 774314403806253056,
 773985732834758656,
 773922284943896577,
 773704687002451968,
 773670353721753600,
 773547596996571136,
 773336787167145985,
 773308824254029826,
 773247561583001600,
 773191612633579521,
 772877495989305348,
 772826264096874500,
 772615324260794368,
 772581559778025472,
 772193107915964416,
 772152991789019136,
 772117678702071809,
 772114945936949249,
 772102971039580160,
 771908950375665664,
 771770456517009408,
 771500966810099713,
 771380798096281600,
 771171053431250945,
 771136648247640064,
 771102124360998913,
 771014301343748096,
 771004394259247104,
 770787852854652928,
 770772759874076672,
 770743923962707968,
 770655142660169732,
 770414278348247044,
 770293558247038976,
 770093767776997377,
 770069151037685760,
 769940425801170949,
 769695466921623552,
 769335591808995329,
 769212283578875904,
 768970937022709760,
 768909767477751808,
 768855141948723200,
 768609597686943744,
 768596291618299904,
 768554158521745409,
 768473857036525572,
 768193404517830656,
 767884188863397888,
 767754930266464257,
 767500508068192258,
 767191397493538821,
 767122157629476866,
 766864461642756096,
 766793450729734144,
 766714921925144576,
 766693177336135680,
 766423258543644672,
 766313316352462849,
 766078092750233600,
 766069199026450432,
 766008592277377025,
 765719909049503744,
 765669560888528897,
 765395769549590528,
 765371061932261376,
 765222098633691136,
 764857477905154048,
 764259802650378240,
 763956972077010945,
 763837565564780549,
 763183847194451968,
 763167063695355904,
 763103485927849985,
 762699858130116608,
 762471784394268675,
 762464539388485633,
 762316489655476224,
 762035686371364864,
 761976711479193600,
 761750502866649088,
 761745352076779520,
 761672994376806400,
 761599872357261312,
 761371037149827077,
 761334018830917632,
 761292947749015552,
 761227390836215808,
 761004547850530816,
 760893934457552897,
 760656994973933572,
 760641137271070720,
 760539183865880579,
 760521673607086080,
 760290219849637889,
 760252756032651264,
 760190180481531904,
 760153949710192640,
 759943073749200896,
 759923798737051648,
 759846353224826880,
 759793422261743616,
 759566828574212096,
 759557299618865152,
 759447681597108224,
 759446261539934208,
 759197388317847553,
 759159934323924993,
 759099523532779520,
 759047813560868866,
 758854675097526272,
 758828659922702336,
 758740312047005698,
 758474966123810816,
 758467244762497024,
 758405701903519748,
 758355060040593408,
 758099635764359168,
 758041019896193024,
 757741869644341248,
 757729163776290825,
 757725642876129280,
 757611664640446465,
 757597904299253760,
 757596066325864448,
 757400162377592832,
 757393109802180609,
 757354760399941633,
 756998049151549440,
 756939218950160384,
 756651752796094464,
 756526248105566208,
 756303284449767430,
 756288534030475264,
 756275833623502848,
 755955933503782912,
 755206590534418437,
 755110668769038337,
 754874841593970688,
 754856583969079297,
 754747087846248448,
 754482103782404096,
 754449512966619136,
 754120377874386944,
 754011816964026368,
 753655901052166144,
 753420520834629632,
 753398408988139520,
 753375668877008896,
 753298634498793472,
 753294487569522689,
 753039830821511168,
 753026973505581056,
 752932432744185856,
 752917284578922496,
 752701944171524096,
 752682090207055872,
 752660715232722944,
 752568224206688256,
 752519690950500352,
 752334515931054080,
 752309394570878976,
 752173152931807232,
 751950017322246144,
 751937170840121344,
 751830394383790080,
 751793661361422336,
 751598357617971201,
 751583847268179968,
 751538714308972544,
 751456908746354688,
 751251247299190784,
 751205363882532864,
 751132876104687617,
 750868782890057730,
 750719632563142656,
 750506206503038976,
 750429297815552001,
 750383411068534784,
 750381685133418496,
 750147208377409536,
 750132105863102464,
 750117059602808832,
 750101899009982464,
 750086836815486976,
 750071704093859840,
 750056684286914561,
 750041628174217216,
 750026558547456000,
 750011400160841729,
 749996283729883136,
 749981277374128128,
 749774190421639168,
 749417653287129088,
 749403093750648834,
 749395845976588288,
 749317047558017024,
 749075273010798592,
 749064354620928000,
 749036806121881602,
 748977405889503236,
 748932637671223296,
 748705597323898880,
 748699167502000129,
 748692773788876800,
 748575535303884801,
 748568946752774144,
 748346686624440324,
 748337862848962560,
 748324050481647620,
 748307329658011649,
 748220828303695873,
 ...]

dog_clean =pd.melt(dog_clean, id_vars = ['tweet_id', 'in_reply_to_status_id', 'in_reply_to_user_id', 'retweeted_status_id',
                                       'retweeted_status_user_id', 'timestamp', 'source', 'text', 'retweeted_status_timestamp',
                                       'expanded_urls', 'rating_numerator', 'rating_denominator', 'name'], 
        var_name = 'type_toberemoved', value_name = 'type')

dog_clean

dog_clean = dog_clean.drop('type_toberemoved', axis =1)

dog_clean

print(dog_clean.type.value_counts())

None       9030
pupper      257
doggo        97
puppo        30
floofer      10
Name: type, dtype: int64

#Merging dog_clean and additional_tweet_data_clean.
#We will set the how parameter to 'inner'; that way we only deal with tweets that are in both tables.

combine_clean = pd.merge(dog_clean, additional_tweet_data_clean, on = ['tweet_id'], how = 'inner')

combine_clean

#Merging 'inner' again for same reason.
combine_clean_all = pd.merge(combine_clean,dog_images, on ='tweet_id', how = 'inner')

combine_clean_all

combine_clean_all.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 8280 entries, 0 to 8279
Data columns (total 27 columns):
tweet_id                      8280 non-null int64
in_reply_to_status_id         92 non-null float64
in_reply_to_user_id           92 non-null float64
retweeted_status_id           304 non-null float64
retweeted_status_user_id      304 non-null float64
timestamp                     8280 non-null object
source                        8280 non-null object
text                          8280 non-null object
retweeted_status_timestamp    304 non-null object
expanded_urls                 8280 non-null object
rating_numerator              8280 non-null int64
rating_denominator            8280 non-null int64
name                          8280 non-null object
type                          8280 non-null object
favorite_count                8280 non-null int64
retweet_count                 8280 non-null int64
jpg_url                       8280 non-null object
img_num                       8280 non-null int64
p1                            8280 non-null object
p1_conf                       8280 non-null float64
p1_dog                        8280 non-null bool
p2                            8280 non-null object
p2_conf                       8280 non-null float64
p2_dog                        8280 non-null bool
p3                            8280 non-null object
p3_conf                       8280 non-null float64
p3_dog                        8280 non-null bool
dtypes: bool(3), float64(7), int64(6), object(11)
memory usage: 1.6+ MB

Quality Tasks 1) We only want original ratings. So we don't want tweets replying to another tweet, or retweeted tweets.

2) the wrong data type: tweet_id, in_reply_to_status_id, in_reply_to_user_id, retweeted_status_id, retweeted_status_user_id, and timestamp.

3) There are a few tweets that have been deleted. I.e missing API data

4) We are missing data for the dog breed predictions.

5) Some names in the name columns can't possibly be dog names. (a, the, an, this...)

we only want tweets that do not have a in_reply_to_status_id, or a retweeted_statusid. We will also drop the columns associated with replys and retweets.¶

combine_clean_all[~combine_clean_all.in_reply_to_status_id.isnull()].tweet_id

488     863079547188785154
489     863079547188785154
490     863079547188785154
491     863079547188785154
600     856526610513747968
601     856526610513747968
602     856526610513747968
603     856526610513747968
796     844979544864018432
797     844979544864018432
798     844979544864018432
799     844979544864018432
1816    802265048156610565
1817    802265048156610565
1818    802265048156610565
1819    802265048156610565
3316    746906459439529985
3317    746906459439529985
3318    746906459439529985
3319    746906459439529985
3324    746818907684614144
3325    746818907684614144
3326    746818907684614144
3327    746818907684614144
3712    729838605770891264
3713    729838605770891264
3714    729838605770891264
3715    729838605770891264
4436    705786532653883392
4437    705786532653883392
               ...        
6270    675870721063669760
6271    675870721063669760
6304    675707330206547968
6305    675707330206547968
6306    675707330206547968
6307    675707330206547968
6360    675349384339542016
6361    675349384339542016
6362    675349384339542016
6363    675349384339542016
6424    674999807681908736
6425    674999807681908736
6426    674999807681908736
6427    674999807681908736
6436    674793399141146624
6437    674793399141146624
6438    674793399141146624
6439    674793399141146624
6464    674754018082705410
6465    674754018082705410
6466    674754018082705410
6467    674754018082705410
7020    671729906628341761
7021    671729906628341761
7022    671729906628341761
7023    671729906628341761
7544    669353438988365824
7545    669353438988365824
7546    669353438988365824
7547    669353438988365824
Name: tweet_id, Length: 92, dtype: int64

#dropping reply tweet
combine_clean_all = combine_clean_all[combine_clean_all.in_reply_to_status_id.isnull()]

#dropping retweeted tweets
combine_clean_all = combine_clean_all[combine_clean_all.retweeted_status_id.isnull()]

#dropping columns related to tweets that were retweeted or reply tweets
combine_clean_all = combine_clean_all.drop(labels = ['in_reply_to_status_id', 'in_reply_to_user_id', 'retweeted_status_id',
                           'retweeted_status_user_id', 'retweeted_status_timestamp'], axis = 1 )

combine_clean_all

combine_clean_all.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 7884 entries, 0 to 8279
Data columns (total 22 columns):
tweet_id              7884 non-null int64
timestamp             7884 non-null object
source                7884 non-null object
text                  7884 non-null object
expanded_urls         7884 non-null object
rating_numerator      7884 non-null int64
rating_denominator    7884 non-null int64
name                  7884 non-null object
type                  7884 non-null object
favorite_count        7884 non-null int64
retweet_count         7884 non-null int64
jpg_url               7884 non-null object
img_num               7884 non-null int64
p1                    7884 non-null object
p1_conf               7884 non-null float64
p1_dog                7884 non-null bool
p2                    7884 non-null object
p2_conf               7884 non-null float64
p2_dog                7884 non-null bool
p3                    7884 non-null object
p3_conf               7884 non-null float64
p3_dog                7884 non-null bool
dtypes: bool(3), float64(3), int64(6), object(10)
memory usage: 1.2+ MB

Convert the tweet_id to string. Convert timestamp to datetime. The following variables need to be switched to category data type: type, p1, p2, and p3. The following variables need to be switched to a boolean data type: p1_dog, p2_dog, p3_dog. The following data types need to be switched to a float data type: rating_numerator, rating_numerator.¶

#converting tweet_id to string
combine_clean_all.tweet_id = combine_clean_all.tweet_id.astype('str')

#converting timestamp to datetime
combine_clean_all.timestamp = pd.to_datetime(combine_clean_all.timestamp)
#Switch type, p1 ,p2, and p3 to category.
combine_clean_all.p1 = combine_clean_all.p1.astype('category')
combine_clean_all.p2 = combine_clean_all.p2.astype('category')
combine_clean_all.p3 = combine_clean_all.p3.astype('category')
combine_clean_all.type = combine_clean_all.type.astype('category')

#Switch p1_dog, p2_dog, and p3_dog to boolean
combine_clean_all.p1_dog = combine_clean_all.p1_dog.astype('bool')
combine_clean_all.p2_dog = combine_clean_all.p2_dog.astype('bool')
combine_clean_all.p3_dog = combine_clean_all.p3_dog.astype('bool')

#Switch rating_numerator and rating_denominator to float.
combine_clean_all.rating_numerator = combine_clean_all.rating_numerator.astype(float)
combine_clean_all.rating_denominator = combine_clean_all.rating_denominator.astype(float)

combine_clean_all.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 7884 entries, 0 to 8279
Data columns (total 22 columns):
tweet_id              7884 non-null object
timestamp             7884 non-null datetime64[ns]
source                7884 non-null object
text                  7884 non-null object
expanded_urls         7884 non-null object
rating_numerator      7884 non-null float64
rating_denominator    7884 non-null float64
name                  7884 non-null object
type                  7884 non-null category
favorite_count        7884 non-null int64
retweet_count         7884 non-null int64
jpg_url               7884 non-null object
img_num               7884 non-null int64
p1                    7884 non-null category
p1_conf               7884 non-null float64
p1_dog                7884 non-null bool
p2                    7884 non-null category
p2_conf               7884 non-null float64
p2_dog                7884 non-null bool
p3                    7884 non-null category
p3_conf               7884 non-null float64
p3_dog                7884 non-null bool
dtypes: bool(3), category(4), datetime64[ns](1), float64(5), int64(3), object(6)
memory usage: 1.1+ MB

type(combine_clean_all['tweet_id'][0])

str

combine_clean_all.sample(5)

Drop rows that do not have a jpg_url column as tweets without a jpg_url do not contain images.¶

combine_clean_all =combine_clean_all[~combine_clean_all.jpg_url.isnull()]

combine_clean_all.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 7884 entries, 0 to 8279
Data columns (total 22 columns):
tweet_id              7884 non-null object
timestamp             7884 non-null datetime64[ns]
source                7884 non-null object
text                  7884 non-null object
expanded_urls         7884 non-null object
rating_numerator      7884 non-null float64
rating_denominator    7884 non-null float64
name                  7884 non-null object
type                  7884 non-null category
favorite_count        7884 non-null int64
retweet_count         7884 non-null int64
jpg_url               7884 non-null object
img_num               7884 non-null int64
p1                    7884 non-null category
p1_conf               7884 non-null float64
p1_dog                7884 non-null bool
p2                    7884 non-null category
p2_conf               7884 non-null float64
p2_dog                7884 non-null bool
p3                    7884 non-null category
p3_conf               7884 non-null float64
p3_dog                7884 non-null bool
dtypes: bool(3), category(4), datetime64[ns](1), float64(5), int64(3), object(6)
memory usage: 1.1+ MB

combine_clean_all.name.value_counts()

None         2096
a             220
Charlie        44
Oliver         40
Lucy           40
Cooper         40
Tucker         36
Penny          36
Sadie          32
Winston        32
Daisy          28
the            28
Toby           28
Lola           28
Bo             24
Jax            24
Koda           24
Bella          24
Stanley        24
an             24
Oscar          20
Louis          20
Scout          20
Rusty          20
Chester        20
Milo           20
Bailey         20
Dave           20
Buddy          20
Leo            20
             ... 
Emanuel         4
Herb            4
Fred            4
Chase           4
Tove            4
actually        4
Puff            4
Shikha          4
Hermione        4
Jeffrie         4
Brownie         4
Jiminus         4
Arlen           4
Schnitzel       4
Edmund          4
Antony          4
Kaiya           4
Ivar            4
Stewie          4
Strudel         4
Kendall         4
Patch           4
Bell            4
Kenzie          4
Pip             4
Sparky          4
Eleanor         4
Tedrick         4
Carter          4
Asher           4
Name: name, Length: 935, dtype: int64

<class 'pandas.core.frame.DataFrame'>
Int64Index: 7884 entries, 0 to 8279
Data columns (total 22 columns):
tweet_id              7884 non-null object
timestamp             7884 non-null datetime64[ns]
source                7884 non-null object
text                  7884 non-null object
expanded_urls         7884 non-null object
rating_numerator      7884 non-null float64
rating_denominator    7884 non-null float64
name                  7884 non-null object
type                  7884 non-null category
favorite_count        7884 non-null int64
retweet_count         7884 non-null int64
jpg_url               7884 non-null object
img_num               7884 non-null int64
p1                    7884 non-null category
p1_conf               7884 non-null float64
p1_dog                7884 non-null bool
p2                    7884 non-null category
p2_conf               7884 non-null float64
p2_dog                7884 non-null bool
p3                    7884 non-null category
p3_conf               7884 non-null float64
p3_dog                7884 non-null bool
dtypes: bool(3), category(4), datetime64[ns](1), float64(5), int64(3), object(6)
memory usage: 1.1+ MB

combine_clean_all.name.value_counts()

None         2372
Charlie        44
Lucy           40
Oliver         40
Cooper         40
Penny          36
Tucker         36
Sadie          32
Winston        32
Lola           28
Daisy          28
Toby           28
Koda           24
Bo             24
Stanley        24
Bella          24
Jax            24
Scout          20
Oscar          20
Louis          20
Rusty          20
Buddy          20
Chester        20
Bailey         20
Milo           20
Dave           20
Zoey           20
Leo            20
Oakley         16
Scooter        16
             ... 
Dylan           4
Brudge          4
Emanuel         4
Dante           4
Carter          4
Tedrick         4
Eleanor         4
Fabio           4
Cheesy          4
Darla           4
Jessifer        4
Puff            4
Hermione        4
Jeffrie         4
Brownie         4
Jiminus         4
Arlen           4
Schnitzel       4
Edmund          4
Antony          4
Kaiya           4
Ivar            4
Stewie          4
Strudel         4
Kendall         4
Patch           4
Bell            4
Kenzie          4
Pip             4
Clyde           4
Name: name, Length: 936, dtype: int64

combine_clean_all.duplicated()

0       False
1        True
2        True
3        True
4       False
5        True
6        True
7        True
8       False
9        True
10       True
11       True
12      False
13       True
14       True
15       True
16      False
17       True
18       True
19       True
20      False
21       True
22       True
23       True
24      False
25       True
26       True
27       True
28      False
29       True
        ...  
7854     True
7855     True
7856    False
7857     True
7858     True
7859     True
7860    False
7861     True
7862     True
7863     True
7864    False
7865     True
7866     True
7867     True
7868    False
7869     True
7870     True
7871     True
7872    False
7873     True
7874     True
7875     True
7876    False
7877     True
7878     True
7879     True
7880    False
7881     True
7882     True
7883     True
Length: 7884, dtype: bool

None         2372
Charlie        44
Lucy           40
Oliver         40
Cooper         40
Penny          36
Tucker         36
Sadie          32
Winston        32
Lola           28
Daisy          28
Toby           28
Koda           24
Bo             24
Stanley        24
Bella          24
Jax            24
Scout          20
Oscar          20
Louis          20
Rusty          20
Buddy          20
Chester        20
Bailey         20
Milo           20
Dave           20
Zoey           20
Leo            20
Oakley         16
Scooter        16
             ... 
Dylan           4
Brudge          4
Emanuel         4
Dante           4
Carter          4
Tedrick         4
Eleanor         4
Fabio           4
Cheesy          4
Darla           4
Jessifer        4
Puff            4
Hermione        4
Jeffrie         4
Brownie         4
Jiminus         4
Arlen           4
Schnitzel       4
Edmund          4
Antony          4
Kaiya           4
Ivar            4
Stewie          4
Strudel         4
Kendall         4
Patch           4
Bell            4
Kenzie          4
Pip             4
Clyde           4
Name: name, Length: 936, dtype: int64

combine_clean_all.drop_duplicates()

combine_clean_all.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 7884 entries, 0 to 7883
Data columns (total 22 columns):
tweet_id              7884 non-null object
timestamp             7884 non-null datetime64[ns]
source                7884 non-null object
text                  7884 non-null object
expanded_urls         7884 non-null object
rating_numerator      7884 non-null float64
rating_denominator    7884 non-null float64
name                  7884 non-null object
type                  7884 non-null category
favorite_count        7884 non-null int64
retweet_count         7884 non-null int64
jpg_url               7884 non-null object
img_num               7884 non-null int64
p1                    7884 non-null category
p1_conf               7884 non-null float64
p1_dog                7884 non-null bool
p2                    7884 non-null category
p2_conf               7884 non-null float64
p2_dog                7884 non-null bool
p3                    7884 non-null category
p3_conf               7884 non-null float64
p3_dog                7884 non-null bool
dtypes: bool(3), category(4), datetime64[ns](1), float64(5), int64(3), object(6)
memory usage: 1.4+ MB

exploring and visualizing the data¶

combine_clean_all['type'].value_counts()

None       7571
pupper      209
doggo        73
puppo        23
floofer       8
Name: type, dtype: int64

import matplotlib.pyplot as plt
combine_clean_all['type'].value_counts().plot(kind='bar')

<matplotlib.axes._subplots.AxesSubplot at 0x7f1f3cec0048>

<matplotlib.axes._subplots.AxesSubplot at 0x7f1f3cf9ce80>

toptype=combine_clean_all['type'].value_counts().plot(kind='bar')

toptype=combine_clean_all['type'].value_counts()
toptype.sort_values(ascending=True)[:3].plot(kind="bar")

<matplotlib.axes._subplots.AxesSubplot at 0x7f1f3ccceef0>

combine_clean_all.describe()

The variables favorite_count, and retweet_count seem to have significantly greater means than medians. Their standard deviation is even greater than the mean. I think this means the favorite_count and retweet counts are heavily skewed.

plt.hist(x = combine_clean_all.rating_numerator, bins = 1000)
plt.xlim(0,20)
plt.show()
combine_clean_all.rating_numerator.value_counts()

12.0      1784
10.0      1668
11.0      1568
13.0      1012
9.0        600
8.0        380
7.0        208
14.0       132
5.0        132
6.0        128
3.0         76
4.0         64
2.0         36
1.0         20
24.0         4
80.0         4
0.0          4
1776.0       4
60.0         4
99.0         4
26.0         4
144.0        4
88.0         4
121.0        4
45.0         4
420.0        4
75.0         4
165.0        4
84.0         4
27.0         4
50.0         4
204.0        4
44.0         4
Name: rating_numerator, dtype: int64

plt.figure(1, figsize = (11, 8.5))
plt.hist(x = combine_clean_all.retweet_count, bins = 100)
plt.title('Distribution of Retweet Counts')
plt.xlabel('Retweet Counts')
plt.ylabel('Frequency')
plt.show()

plt.figure(1, figsize = (11, 8.5))
plt.hist(x = combine_clean_all.favorite_count, bins = 100)
plt.title('Distribution of Favorite Counts')
plt.xlabel('Favorite Counts')
plt.ylabel('Frequency')
plt.show()

conclusion :The distribution of retweet_count and favorite_count look similar, but retweet_count is lower than favorite_count. I would guess that these numbers are related to timestamp.¶

# log transformation of the data
to_log = ['favorite_count', 'retweet_count']
df_logged = combine_clean_all[to_log].applymap(lambda x: np.log10(x))

plt.hist(x = df_logged.favorite_count, bins = 100)
plt.show()

plt.hist(x = df_logged.retweet_count, bins = 100)
plt.show()

plt.plot(combine_clean_all.favorite_count, combine_clean_all.retweet_count, marker='o', linestyle='', ms=2 )
plt.show()

plt.figure(1, figsize = (11, 8.5))
plt.plot(df_logged.favorite_count, df_logged.retweet_count, marker='o', linestyle='', ms=2 )
plt.title('Log(Retweet Count) versus Log(Favorite Count)')
plt.xlabel('Log(Favorite Count)')
plt.ylabel('Log(Retweet Count)')
plt.show()
np.corrcoef(df_logged.retweet_count, df_logged.favorite_count)[0][1]

0.96853041055316491

plt.figure(1, figsize = (11, 8.5))
plt.plot(combine_clean_all.timestamp ,df_logged.retweet_count, marker = 'o', linestyle = '', ms = 2)
plt.title('Favorite Count Over Time')
plt.xlabel('Time (Year - Month)')
plt.ylabel('Log(Favorite Count)')
plt.show()

conclusion: dog_rates started to gain popularity very quickly upon first opening the account.¶

combine_clean_all.year = pd.Series(list(range(len(combine_clean_all))))
combine_clean_all.month = pd.Series(list(range(len(combine_clean_all))))
for idx, row in combine_clean_all.iterrows():
    combine_clean_all.loc[idx,'year'] = row.timestamp.year
    combine_clean_all.loc[idx, 'month'] = row.timestamp.month

combine_clean_all.groupby(['month', 'year']).tweet_id.count()

month  year  
1.0    2016.0     664
       2017.0     264
2.0    2016.0     432
       2017.0     256
3.0    2016.0     472
       2017.0     188
4.0    2016.0     216
       2017.0     160
5.0    2016.0     224
       2017.0     168
6.0    2016.0     316
       2017.0     176
7.0    2016.0     352
       2017.0     196
8.0    2016.0     236
       2017.0       8
9.0    2016.0     252
10.0   2016.0     260
11.0   2015.0    1180
       2016.0     208
12.0   2015.0    1440
       2016.0     216
Name: tweet_id, dtype: int64

nmonth = list(range(22))
smonth = ['11/2015', '12/2015', '1/2016', '2/2016', '3/2016', '4/2016', ]
tweets_per_month=[264, 332, 157, 102, 113, 54, 55, 78, 87, 58, 63, 65, 52, 54, 66, 64, 47, 40, 42, 44, 49, 2]
plt.figure(1, figsize = (11, 8.5))
plt.plot(nmonth, tweets_per_month, marker= 'o', ms=3)
plt.title('Tweets per Month Over Time')
plt.xlabel('Month (Number of Months since Account\'s creation)')
plt.ylabel('Number of Tweets')
plt.show()

plt.figure(1, figsize = (13, 8.5))
plt.plot(combine_clean_all.timestamp, combine_clean_all.rating_numerator, marker='o', linestyle='', ms = 2)
plt.ylim(0,15)
plt.title('Rating Over Time')
plt.ylabel('Rating (numerator)')
plt.xlabel('Time (Year - Month)')
plt.show()

conclusion :it looks like as time went on dog_rates stopped rating dogs under 10.

	tweet_id	jpg_url	img_num	p1	p1_conf	p1_dog	p2	p2_conf	p2_dog	p3	p3_conf	p3_dog
0	666020888022790149	https://pbs.twimg.com/media/CT4udn0WwAA0aMy.jpg	1	Welsh_springer_spaniel	0.465074	True	collie	0.156665	True	Shetland_sheepdog	0.061428	True
1	666029285002620928	https://pbs.twimg.com/media/CT42GRgUYAA5iDo.jpg	1	redbone	0.506826	True	miniature_pinscher	0.074192	True	Rhodesian_ridgeback	0.072010	True
2	666033412701032449	https://pbs.twimg.com/media/CT4521TWwAEvMyu.jpg	1	German_shepherd	0.596461	True	malinois	0.138584	True	bloodhound	0.116197	True
3	666044226329800704	https://pbs.twimg.com/media/CT5Dr8HUEAA-lEu.jpg	1	Rhodesian_ridgeback	0.408143	True	redbone	0.360687	True	miniature_pinscher	0.222752	True
4	666049248165822465	https://pbs.twimg.com/media/CT5IQmsXIAAKY4A.jpg	1	miniature_pinscher	0.560311	True	Rottweiler	0.243682	True	Doberman	0.154629	True
5	666050758794694657	https://pbs.twimg.com/media/CT5Jof1WUAEuVxN.jpg	1	Bernese_mountain_dog	0.651137	True	English_springer	0.263788	True	Greater_Swiss_Mountain_dog	0.016199	True
6	666051853826850816	https://pbs.twimg.com/media/CT5KoJ1WoAAJash.jpg	1	box_turtle	0.933012	False	mud_turtle	0.045885	False	terrapin	0.017885	False
7	666055525042405380	https://pbs.twimg.com/media/CT5N9tpXIAAifs1.jpg	1	chow	0.692517	True	Tibetan_mastiff	0.058279	True	fur_coat	0.054449	False
8	666057090499244032	https://pbs.twimg.com/media/CT5PY90WoAAQGLo.jpg	1	shopping_cart	0.962465	False	shopping_basket	0.014594	False	golden_retriever	0.007959	True
9	666058600524156928	https://pbs.twimg.com/media/CT5Qw94XAAA_2dP.jpg	1	miniature_poodle	0.201493	True	komondor	0.192305	True	soft-coated_wheaten_terrier	0.082086	True

	tweet_id	in_reply_to_status_id	in_reply_to_user_id	retweeted_status_id	retweeted_status_user_id	rating_numerator	rating_denominator
count	2.356000e+03	7.800000e+01	7.800000e+01	1.810000e+02	1.810000e+02	2356.000000	2356.000000
mean	7.427716e+17	7.455079e+17	2.014171e+16	7.720400e+17	1.241698e+16	13.126486	10.455433
std	6.856705e+16	7.582492e+16	1.252797e+17	6.236928e+16	9.599254e+16	45.876648	6.745237
min	6.660209e+17	6.658147e+17	1.185634e+07	6.661041e+17	7.832140e+05	0.000000	0.000000
25%	6.783989e+17	6.757419e+17	3.086374e+08	7.186315e+17	4.196984e+09	10.000000	10.000000
50%	7.196279e+17	7.038708e+17	4.196984e+09	7.804657e+17	4.196984e+09	11.000000	10.000000
75%	7.993373e+17	8.257804e+17	4.196984e+09	8.203146e+17	4.196984e+09	12.000000	10.000000
max	8.924206e+17	8.862664e+17	8.405479e+17	8.874740e+17	7.874618e+17	1776.000000	170.000000

	tweet_id	img_num	p1_conf	p2_conf	p3_conf
count	2.075000e+03	2075.000000	2075.000000	2.075000e+03	2.075000e+03
mean	7.384514e+17	1.203855	0.594548	1.345886e-01	6.032417e-02
std	6.785203e+16	0.561875	0.271174	1.006657e-01	5.090593e-02
min	6.660209e+17	1.000000	0.044333	1.011300e-08	1.740170e-10
25%	6.764835e+17	1.000000	0.364412	5.388625e-02	1.622240e-02
50%	7.119988e+17	1.000000	0.588230	1.181810e-01	4.944380e-02
75%	7.932034e+17	1.000000	0.843855	1.955655e-01	9.180755e-02
max	8.924206e+17	4.000000	1.000000	4.880140e-01	2.734190e-01

	favorite_count	retweet_count	tweet_id
count	2348.000000	2348.000000	2.348000e+03
mean	8113.313032	3074.319847	7.424145e+17
std	12193.072715	5100.139904	6.837627e+16
min	0.000000	0.000000	6.660209e+17
25%	1410.000000	613.500000	6.783868e+17
50%	3570.500000	1435.500000	7.191522e+17
75%	10063.250000	3579.250000	7.987607e+17
max	143573.000000	78378.000000	8.924206e+17

	rating_numerator	rating_denominator	favorite_count	retweet_count	img_num	p1_conf	p2_conf	p3_conf
count	7884.000000	7884.000000	7884.000000	7884.000000	7884.000000	7884.000000	7.884000e+03	7.884000e+03
mean	12.223237	10.477423	8964.528666	2770.847793	1.201928	0.594558	1.345850e-01	6.016556e-02
std	41.626111	6.851971	12678.638196	4767.126617	0.558914	0.272075	1.010335e-01	5.093187e-02
min	0.000000	2.000000	80.000000	14.000000	1.000000	0.044333	1.011300e-08	1.740170e-10
25%	10.000000	10.000000	1962.000000	620.000000	1.000000	0.362925	5.328100e-02	1.605590e-02
50%	11.000000	10.000000	4090.000000	1347.000000	1.000000	0.587764	1.173970e-01	4.944380e-02
75%	12.000000	10.000000	11288.000000	3185.000000	1.000000	0.848362	1.955730e-01	9.157150e-02
max	1776.000000	170.000000	143573.000000	78378.000000	4.000000	1.000000	4.880140e-01	2.734190e-01

	tweet_id	in_reply_to_status_id	in_reply_to_user_id	timestamp	source	text	retweeted_status_id	retweeted_status_user_id	retweeted_status_timestamp	expanded_urls	rating_numerator	rating_denominator	name	doggo	floofer	pupper	puppo
0	892420643555336193	NaN	NaN	2017-08-01 16:23:56 +0000	<a href="http://twitter.com/download/iphone" r...	This is Phineas. He's a mystical boy. Only eve...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/892420643...	13	10	Phineas	None	None	None	None
1	892177421306343426	NaN	NaN	2017-08-01 00:17:27 +0000	<a href="http://twitter.com/download/iphone" r...	This is Tilly. She's just checking pup on you....	NaN	NaN	NaN	https://twitter.com/dog_rates/status/892177421...	13	10	Tilly	None	None	None	None
2	891815181378084864	NaN	NaN	2017-07-31 00:18:03 +0000	<a href="http://twitter.com/download/iphone" r...	This is Archie. He is a rare Norwegian Pouncin...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/891815181...	12	10	Archie	None	None	None	None
3	891689557279858688	NaN	NaN	2017-07-30 15:58:51 +0000	<a href="http://twitter.com/download/iphone" r...	This is Darla. She commenced a snooze mid meal...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/891689557...	13	10	Darla	None	None	None	None
4	891327558926688256	NaN	NaN	2017-07-29 16:00:24 +0000	<a href="http://twitter.com/download/iphone" r...	This is Franklin. He would like you to stop ca...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/891327558...	12	10	Franklin	None	None	None	None
5	891087950875897856	NaN	NaN	2017-07-29 00:08:17 +0000	<a href="http://twitter.com/download/iphone" r...	Here we have a majestic great white breaching ...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/891087950...	13	10	None	None	None	None	None
6	890971913173991426	NaN	NaN	2017-07-28 16:27:12 +0000	<a href="http://twitter.com/download/iphone" r...	Meet Jax. He enjoys ice cream so much he gets ...	NaN	NaN	NaN	https://gofundme.com/ydvmve-surgery-for-jax,ht...	13	10	Jax	None	None	None	None
7	890729181411237888	NaN	NaN	2017-07-28 00:22:40 +0000	<a href="http://twitter.com/download/iphone" r...	When you watch your owner call another dog a g...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/890729181...	13	10	None	None	None	None	None
8	890609185150312448	NaN	NaN	2017-07-27 16:25:51 +0000	<a href="http://twitter.com/download/iphone" r...	This is Zoey. She doesn't want to be one of th...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/890609185...	13	10	Zoey	None	None	None	None
9	890240255349198849	NaN	NaN	2017-07-26 15:59:51 +0000	<a href="http://twitter.com/download/iphone" r...	This is Cassie. She is a college pup. Studying...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/890240255...	14	10	Cassie	doggo	None	None	None

	tweet_id	in_reply_to_status_id	in_reply_to_user_id	timestamp	source	text	retweeted_status_id	retweeted_status_user_id	retweeted_status_timestamp	expanded_urls	rating_numerator	rating_denominator	name	doggo	floofer	pupper	puppo
1528	690348396616552449	NaN	NaN	2016-01-22 01:40:58 +0000	<a href="http://vine.co" rel="nofollow">Vine -...	This is Oddie. He's trying to communicate. 12/...	NaN	NaN	NaN	https://vine.co/v/iejBWerY9X2	12	10	Oddie	None	None	None	None
981	749417653287129088	NaN	NaN	2016-07-03 01:41:06 +0000	<a href="http://twitter.com/download/iphone" r...	This is Finn. He's the most unphotogenic puppe...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/749417653...	11	10	Finn	None	None	pupper	None
1943	673709992831262724	NaN	NaN	2015-12-07 03:45:53 +0000	<a href="http://twitter.com/download/iphone" r...	I know a lot of you are studying for finals. G...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/673709992...	12	10	None	None	None	None	None
1709	680609293079592961	NaN	NaN	2015-12-26 04:41:15 +0000	<a href="http://twitter.com/download/iphone" r...	This is Brody. That is his chair. He loves his...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/680609293...	9	10	Brody	None	None	None	None
195	855138241867124737	NaN	NaN	2017-04-20 19:16:59 +0000	<a href="http://twitter.com/download/iphone" r...	RT @frasercampbell_: oh my... what's that... b...	8.551225e+17	7.475543e+17	2017-04-20 18:14:33 +0000	https://twitter.com/frasercampbell_/status/855...	14	10	None	None	None	None	None
1506	691756958957883396	NaN	NaN	2016-01-25 22:58:05 +0000	<a href="http://twitter.com/download/iphone" r...	THE BRITISH ARE COMING\nTHE BRITISH ARE COMING...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/691756958...	10	10	None	None	None	None	None
2185	668986018524233728	NaN	NaN	2015-11-24 02:54:30 +0000	<a href="http://twitter.com/download/iphone" r...	This is Ruby. She's a Bimmington Fettuccini. O...	NaN	NaN	NaN	https://twitter.com/dog_rates/status/668986018...	9	10	Ruby	None	None	None	None

	tweet_id	timestamp	source	text	expanded_urls	rating_numerator	rating_denominator	name	type	favorite_count	...	img_num	p1	p1_conf	p1_dog	p2	p2_conf	p2_dog	p3	p3_conf	p3_dog
2615	771136648247640064	2016-09-01 00:04:38	<a href="http://twitter.com/download/iphone" r...	This is Dixie. She wants to be a ship captain....	https://twitter.com/dog_rates/status/771136648...	11.0	10.0	Dixie	None	10100	...	1	bathtub	0.368660	False	golden_retriever	0.297402	True	tub	0.201711	False
1571	813202720496779264	2016-12-26 02:00:11	<a href="http://twitter.com/download/iphone" r...	Here's a doggo who has concluded that Christma...	https://twitter.com/dog_rates/status/813202720...	11.0	10.0	None	None	10085	...	1	cocker_spaniel	0.701852	True	golden_retriever	0.120345	True	Labrador_retriever	0.036320	True
3801	726224900189511680	2016-04-30 01:41:23	<a href="http://twitter.com/download/iphone" r...	I'm getting super heckin frustrated with you a...	https://twitter.com/dog_rates/status/726224900...	9.0	10.0	None	None	4746	...	1	standard_poodle	0.261112	True	cocker_spaniel	0.094785	True	bucket	0.069946	False
1220	826598365270007810	2017-02-01 01:09:42	<a href="http://twitter.com/download/iphone" r...	This is Pawnd... James Pawnd. He's suave af. 1...	https://twitter.com/dog_rates/status/826598365...	13.0	10.0	Pawnd	None	10983	...	1	French_bulldog	0.628119	True	Siamese_cat	0.117397	False	cougar	0.082765	False
3615	735635087207878657	2016-05-26 00:54:06	<a href="http://twitter.com/download/iphone" r...	This is Dakota. He hasn't grow into his skin y...	https://twitter.com/dog_rates/status/735635087...	11.0	10.0	Dakota	None	6690	...	1	pug	0.891871	True	goose	0.014377	False	fur_coat	0.008451	False

	tweet_id	timestamp	source	text	expanded_urls	rating_numerator	rating_denominator	name	type	favorite_count	...	img_num	p1	p1_conf	p1_dog	p2	p2_conf	p2_dog	p3	p3_conf	p3_dog
0	892420643555336193	2017-08-01 16:23:56	<a href="http://twitter.com/download/iphone" r...	This is Phineas. He's a mystical boy. Only eve...	https://twitter.com/dog_rates/status/892420643...	13.0	10.0	Phineas	None	39170	...	1	orange	0.097049	False	bagel	0.085851	False	banana	0.076110	False
4	892177421306343426	2017-08-01 00:17:27	<a href="http://twitter.com/download/iphone" r...	This is Tilly. She's just checking pup on you....	https://twitter.com/dog_rates/status/892177421...	13.0	10.0	Tilly	None	33546	...	1	Chihuahua	0.323581	True	Pekinese	0.090647	True	papillon	0.068957	True
8	891815181378084864	2017-07-31 00:18:03	<a href="http://twitter.com/download/iphone" r...	This is Archie. He is a rare Norwegian Pouncin...	https://twitter.com/dog_rates/status/891815181...	12.0	10.0	Archie	None	25281	...	1	Chihuahua	0.716012	True	malamute	0.078253	True	kelpie	0.031379	True
12	891689557279858688	2017-07-30 15:58:51	<a href="http://twitter.com/download/iphone" r...	This is Darla. She commenced a snooze mid meal...	https://twitter.com/dog_rates/status/891689557...	13.0	10.0	Darla	None	42535	...	1	paper_towel	0.170278	False	Labrador_retriever	0.168086	True	spatula	0.040836	False
16	891327558926688256	2017-07-29 16:00:24	<a href="http://twitter.com/download/iphone" r...	This is Franklin. He would like you to stop ca...	https://twitter.com/dog_rates/status/891327558...	12.0	10.0	Franklin	None	40714	...	2	basset	0.555712	True	English_springer	0.225770	True	German_short-haired_pointer	0.175219	True
20	891087950875897856	2017-07-29 00:08:17	<a href="http://twitter.com/download/iphone" r...	Here we have a majestic great white breaching ...	https://twitter.com/dog_rates/status/891087950...	13.0	10.0	None	None	20410	...	1	Chesapeake_Bay_retriever	0.425595	True	Irish_terrier	0.116317	True	Indian_elephant	0.076902	False
24	890971913173991426	2017-07-28 16:27:12	<a href="http://twitter.com/download/iphone" r...	Meet Jax. He enjoys ice cream so much he gets ...	https://gofundme.com/ydvmve-surgery-for-jax,ht...	13.0	10.0	Jax	None	11968	...	1	Appenzeller	0.341703	True	Border_collie	0.199287	True	ice_lolly	0.193548	False
28	890729181411237888	2017-07-28 00:22:40	<a href="http://twitter.com/download/iphone" r...	When you watch your owner call another dog a g...	https://twitter.com/dog_rates/status/890729181...	13.0	10.0	None	None	66189	...	2	Pomeranian	0.566142	True	Eskimo_dog	0.178406	True	Pembroke	0.076507	True
32	890609185150312448	2017-07-27 16:25:51	<a href="http://twitter.com/download/iphone" r...	This is Zoey. She doesn't want to be one of th...	https://twitter.com/dog_rates/status/890609185...	13.0	10.0	Zoey	None	28025	...	1	Irish_terrier	0.487574	True	Irish_setter	0.193054	True	Chesapeake_Bay_retriever	0.118184	True
36	890240255349198849	2017-07-26 15:59:51	<a href="http://twitter.com/download/iphone" r...	This is Cassie. She is a college pup. Studying...	https://twitter.com/dog_rates/status/890240255...	14.0	10.0	Cassie	doggo	32235	...	1	Pembroke	0.511319	True	Cardigan	0.451038	True	Chihuahua	0.029248	True
37	890240255349198849	2017-07-26 15:59:51	<a href="http://twitter.com/download/iphone" r...	This is Cassie. She is a college pup. Studying...	https://twitter.com/dog_rates/status/890240255...	14.0	10.0	Cassie	None	32235	...	1	Pembroke	0.511319	True	Cardigan	0.451038	True	Chihuahua	0.029248	True
40	890006608113172480	2017-07-26 00:31:25	<a href="http://twitter.com/download/iphone" r...	This is Koda. He is a South Australian decksha...	https://twitter.com/dog_rates/status/890006608...	13.0	10.0	Koda	None	30904	...	1	Samoyed	0.957979	True	Pomeranian	0.013884	True	chow	0.008167	True
44	889880896479866881	2017-07-25 16:11:53	<a href="http://twitter.com/download/iphone" r...	This is Bruno. He is a service shark. Only get...	https://twitter.com/dog_rates/status/889880896...	13.0	10.0	Bruno	None	28034	...	1	French_bulldog	0.377417	True	Labrador_retriever	0.151317	True	muzzle	0.082981	False
48	889665388333682689	2017-07-25 01:55:32	<a href="http://twitter.com/download/iphone" r...	Here's a puppo that seems to be on the fence a...	https://twitter.com/dog_rates/status/889665388...	13.0	10.0	None	None	48330	...	1	Pembroke	0.966327	True	Cardigan	0.027356	True	basenji	0.004633	True
51	889665388333682689	2017-07-25 01:55:32	<a href="http://twitter.com/download/iphone" r...	Here's a puppo that seems to be on the fence a...	https://twitter.com/dog_rates/status/889665388...	13.0	10.0	None	puppo	48330	...	1	Pembroke	0.966327	True	Cardigan	0.027356	True	basenji	0.004633	True
52	889638837579907072	2017-07-25 00:10:02	<a href="http://twitter.com/download/iphone" r...	This is Ted. He does his best. Sometimes that'...	https://twitter.com/dog_rates/status/889638837...	12.0	10.0	Ted	None	27434	...	1	French_bulldog	0.991650	True	boxer	0.002129	True	Staffordshire_bullterrier	0.001498	True
56	889531135344209921	2017-07-24 17:02:04	<a href="http://twitter.com/download/iphone" r...	This is Stuart. He's sporting his favorite fan...	https://twitter.com/dog_rates/status/889531135...	13.0	10.0	Stuart	None	15232	...	1	golden_retriever	0.953442	True	Labrador_retriever	0.013834	True	redbone	0.007958	True
59	889531135344209921	2017-07-24 17:02:04	<a href="http://twitter.com/download/iphone" r...	This is Stuart. He's sporting his favorite fan...	https://twitter.com/dog_rates/status/889531135...	13.0	10.0	Stuart	puppo	15232	...	1	golden_retriever	0.953442	True	Labrador_retriever	0.013834	True	redbone	0.007958	True
60	889278841981685760	2017-07-24 00:19:32	<a href="http://twitter.com/download/iphone" r...	This is Oliver. You're witnessing one of his m...	https://twitter.com/dog_rates/status/889278841...	13.0	10.0	Oliver	None	25527	...	1	whippet	0.626152	True	borzoi	0.194742	True	Saluki	0.027351	True
64	888917238123831296	2017-07-23 00:22:39	<a href="http://twitter.com/download/iphone" r...	This is Jim. He found a fren. Taught him how t...	https://twitter.com/dog_rates/status/888917238...	12.0	10.0	Jim	None	29342	...	1	golden_retriever	0.714719	True	Tibetan_mastiff	0.120184	True	Labrador_retriever	0.105506	True
68	888804989199671297	2017-07-22 16:56:37	<a href="http://twitter.com/download/iphone" r...	This is Zeke. He has a new stick. Very proud o...	https://twitter.com/dog_rates/status/888804989...	13.0	10.0	Zeke	None	25833	...	1	golden_retriever	0.469760	True	Labrador_retriever	0.184172	True	English_setter	0.073482	True
72	888554962724278272	2017-07-22 00:23:06	<a href="http://twitter.com/download/iphone" r...	This is Ralphus. He's powering up. Attempting ...	https://twitter.com/dog_rates/status/888554962...	13.0	10.0	Ralphus	None	20118	...	3	Siberian_husky	0.700377	True	Eskimo_dog	0.166511	True	malamute	0.111411	True
76	888078434458587136	2017-07-20 16:49:33	<a href="http://twitter.com/download/iphone" r...	This is Gerald. He was just told he didn't get...	https://twitter.com/dog_rates/status/888078434...	12.0	10.0	Gerald	None	21984	...	1	French_bulldog	0.995026	True	pug	0.000932	True	bull_mastiff	0.000903	True
80	887705289381826560	2017-07-19 16:06:48	<a href="http://twitter.com/download/iphone" r...	This is Jeffrey. He has a monopoly on the pool...	https://twitter.com/dog_rates/status/887705289...	13.0	10.0	Jeffrey	None	30483	...	1	basset	0.821664	True	redbone	0.087582	True	Weimaraner	0.026236	True
84	887517139158093824	2017-07-19 03:39:09	<a href="http://twitter.com/download/iphone" r...	I've yet to rate a Venezuelan Hover Wiener. Th...	https://twitter.com/dog_rates/status/887517139...	14.0	10.0	None	None	46626	...	1	limousine	0.130432	False	tow_truck	0.029175	False	shopping_cart	0.026321	False
88	887473957103951883	2017-07-19 00:47:34	<a href="http://twitter.com/download/iphone" r...	This is Canela. She attempted some fancy porch...	https://twitter.com/dog_rates/status/887473957...	13.0	10.0	Canela	None	69813	...	2	Pembroke	0.809197	True	Rhodesian_ridgeback	0.054950	True	beagle	0.038915	True
92	887343217045368832	2017-07-18 16:08:03	<a href="http://twitter.com/download/iphone" r...	You may not have known you needed to see this ...	https://twitter.com/dog_rates/status/887343217...	13.0	10.0	None	None	33981	...	1	Mexican_hairless	0.330741	True	sea_lion	0.275645	False	Weimaraner	0.134203	True
96	887101392804085760	2017-07-18 00:07:08	<a href="http://twitter.com/download/iphone" r...	This... is a Jubilant Antarctic House Bear. We...	https://twitter.com/dog_rates/status/887101392...	12.0	10.0	None	None	30836	...	1	Samoyed	0.733942	True	Eskimo_dog	0.035029	True	Staffordshire_bullterrier	0.029705	True
100	886983233522544640	2017-07-17 16:17:36	<a href="http://twitter.com/download/iphone" r...	This is Maya. She's very shy. Rarely leaves he...	https://twitter.com/dog_rates/status/886983233...	13.0	10.0	Maya	None	35525	...	2	Chihuahua	0.793469	True	toy_terrier	0.143528	True	can_opener	0.032253	False
104	886736880519319552	2017-07-16 23:58:41	<a href="http://twitter.com/download/iphone" r...	This is Mingus. He's a wonderful father to his...	https://www.gofundme.com/mingusneedsus,https:/...	13.0	10.0	Mingus	None	12186	...	1	kuvasz	0.309706	True	Great_Pyrenees	0.186136	True	Dandie_Dinmont	0.086346	True
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
7764	666411507551481857	2015-11-17 00:24:19	<a href="http://twitter.com/download/iphone" r...	This is quite the dog. Gets really excited whe...	https://twitter.com/dog_rates/status/666411507...	2.0	10.0	None	None	453	...	1	coho	0.404640	False	barracouta	0.271485	False	gar	0.189945	False
7768	666407126856765440	2015-11-17 00:06:54	<a href="http://twitter.com/download/iphone" r...	This is a southern Vesuvius bumblegruff. Can d...	https://twitter.com/dog_rates/status/666407126...	7.0	10.0	None	None	112	...	1	black-and-tan_coonhound	0.529139	True	bloodhound	0.244220	True	flat-coated_retriever	0.173810	True
7772	666396247373291520	2015-11-16 23:23:41	<a href="http://twitter.com/download/iphone" r...	Oh goodness. A super rare northeast Qdoba kang...	https://twitter.com/dog_rates/status/666396247...	9.0	10.0	None	None	170	...	1	Chihuahua	0.978108	True	toy_terrier	0.009397	True	papillon	0.004577	True
7776	666373753744588802	2015-11-16 21:54:18	<a href="http://twitter.com/download/iphone" r...	Those are sunglasses and a jean jacket. 11/10 ...	https://twitter.com/dog_rates/status/666373753...	11.0	10.0	None	None	193	...	1	soft-coated_wheaten_terrier	0.326467	True	Afghan_hound	0.259551	True	briard	0.206803	True
7780	666362758909284353	2015-11-16 21:10:36	<a href="http://twitter.com/download/iphone" r...	Unique dog here. Very small. Lives in containe...	https://twitter.com/dog_rates/status/666362758...	6.0	10.0	None	None	791	...	1	guinea_pig	0.996496	False	skunk	0.002402	False	hamster	0.000461	False
7784	666353288456101888	2015-11-16 20:32:58	<a href="http://twitter.com/download/iphone" r...	Here we have a mixed Asiago from the GalÃ¡pago...	https://twitter.com/dog_rates/status/666353288...	8.0	10.0	None	None	227	...	1	malamute	0.336874	True	Siberian_husky	0.147655	True	Eskimo_dog	0.093412	True
7788	666345417576210432	2015-11-16 20:01:42	<a href="http://twitter.com/download/iphone" r...	Look at this jokester thinking seat belt laws ...	https://twitter.com/dog_rates/status/666345417...	10.0	10.0	None	None	305	...	1	golden_retriever	0.858744	True	Chesapeake_Bay_retriever	0.054787	True	Labrador_retriever	0.014241	True
7792	666337882303524864	2015-11-16 19:31:45	<a href="http://twitter.com/download/iphone" r...	This is an extremely rare horned Parthenon. No...	https://twitter.com/dog_rates/status/666337882...	9.0	10.0	None	None	202	...	1	ox	0.416669	False	Newfoundland	0.278407	True	groenendael	0.102643	True
7796	666293911632134144	2015-11-16 16:37:02	<a href="http://twitter.com/download/iphone" r...	This is a funny dog. Weird toes. Won't come do...	https://twitter.com/dog_rates/status/666293911...	3.0	10.0	None	None	514	...	1	three-toed_sloth	0.914671	False	otter	0.015250	False	great_grey_owl	0.013207	False
7800	666287406224695296	2015-11-16 16:11:11	<a href="http://twitter.com/download/iphone" r...	This is an Albanian 3 1/2 legged Episcopalian...	https://twitter.com/dog_rates/status/666287406...	1.0	2.0	None	None	151	...	1	Maltese_dog	0.857531	True	toy_poodle	0.063064	True	miniature_poodle	0.025581	True
7804	666273097616637952	2015-11-16 15:14:19	<a href="http://twitter.com/download/iphone" r...	Can take selfies 11/10 https://t.co/ws2AMaNwPW	https://twitter.com/dog_rates/status/666273097...	11.0	10.0	None	None	179	...	1	Italian_greyhound	0.176053	True	toy_terrier	0.111884	True	basenji	0.111152	True
7808	666268910803644416	2015-11-16 14:57:41	<a href="http://twitter.com/download/iphone" r...	Very concerned about fellow dog trapped in com...	https://twitter.com/dog_rates/status/666268910...	10.0	10.0	None	None	106	...	1	desktop_computer	0.086502	False	desk	0.085547	False	bookcase	0.079480	False
7812	666104133288665088	2015-11-16 04:02:55	<a href="http://twitter.com/download/iphone" r...	Not familiar with this breed. No tail (weird)....	https://twitter.com/dog_rates/status/666104133...	1.0	10.0	None	None	14579	...	1	hen	0.965932	False	cock	0.033919	False	partridge	0.000052	False
7816	666102155909144576	2015-11-16 03:55:04	<a href="http://twitter.com/download/iphone" r...	Oh my. Here you are seeing an Adobe Setter giv...	https://twitter.com/dog_rates/status/666102155...	11.0	10.0	None	None	80	...	1	English_setter	0.298617	True	Newfoundland	0.149842	True	borzoi	0.133649	True
7820	666099513787052032	2015-11-16 03:44:34	<a href="http://twitter.com/download/iphone" r...	Can stand on stump for what seems like a while...	https://twitter.com/dog_rates/status/666099513...	8.0	10.0	None	None	159	...	1	Lhasa	0.582330	True	Shih-Tzu	0.166192	True	Dandie_Dinmont	0.089688	True
7824	666094000022159362	2015-11-16 03:22:39	<a href="http://twitter.com/download/iphone" r...	This appears to be a Mongolian Presbyterian mi...	https://twitter.com/dog_rates/status/666094000...	9.0	10.0	None	None	166	...	1	bloodhound	0.195217	True	German_shepherd	0.078260	True	malinois	0.075628	True
7828	666082916733198337	2015-11-16 02:38:37	<a href="http://twitter.com/download/iphone" r...	Here we have a well-established sunblockerspan...	https://twitter.com/dog_rates/status/666082916...	6.0	10.0	None	None	120	...	1	pug	0.489814	True	bull_mastiff	0.404722	True	French_bulldog	0.048960	True
7832	666073100786774016	2015-11-16 01:59:36	<a href="http://twitter.com/download/iphone" r...	Let's hope this flight isn't Malaysian (lol). ...	https://twitter.com/dog_rates/status/666073100...	10.0	10.0	None	None	328	...	1	Walker_hound	0.260857	True	English_foxhound	0.175382	True	Ibizan_hound	0.097471	True
7836	666071193221509120	2015-11-16 01:52:02	<a href="http://twitter.com/download/iphone" r...	Here we have a northern speckled Rhododendron....	https://twitter.com/dog_rates/status/666071193...	9.0	10.0	None	None	153	...	1	Gordon_setter	0.503672	True	Yorkshire_terrier	0.174201	True	Pekinese	0.109454	True
7840	666063827256086533	2015-11-16 01:22:45	<a href="http://twitter.com/download/iphone" r...	This is the happiest dog you will ever see. Ve...	https://twitter.com/dog_rates/status/666063827...	10.0	10.0	None	None	486	...	1	golden_retriever	0.775930	True	Tibetan_mastiff	0.093718	True	Labrador_retriever	0.072427	True
7844	666058600524156928	2015-11-16 01:01:59	<a href="http://twitter.com/download/iphone" r...	Here is the Rand Paul of retrievers folks! He'...	https://twitter.com/dog_rates/status/666058600...	8.0	10.0	None	None	115	...	1	miniature_poodle	0.201493	True	komondor	0.192305	True	soft-coated_wheaten_terrier	0.082086	True
7848	666057090499244032	2015-11-16 00:55:59	<a href="http://twitter.com/download/iphone" r...	My oh my. This is a rare blond Canadian terrie...	https://twitter.com/dog_rates/status/666057090...	9.0	10.0	None	None	303	...	1	shopping_cart	0.962465	False	shopping_basket	0.014594	False	golden_retriever	0.007959	True
7852	666055525042405380	2015-11-16 00:49:46	<a href="http://twitter.com/download/iphone" r...	Here is a Siberian heavily armored polar bear ...	https://twitter.com/dog_rates/status/666055525...	10.0	10.0	None	None	446	...	1	chow	0.692517	True	Tibetan_mastiff	0.058279	True	fur_coat	0.054449	False
7856	666051853826850816	2015-11-16 00:35:11	<a href="http://twitter.com/download/iphone" r...	This is an odd dog. Hard on the outside but lo...	https://twitter.com/dog_rates/status/666051853...	2.0	10.0	None	None	1240	...	1	box_turtle	0.933012	False	mud_turtle	0.045885	False	terrapin	0.017885	False
7860	666050758794694657	2015-11-16 00:30:50	<a href="http://twitter.com/download/iphone" r...	This is a truly beautiful English Wilson Staff...	https://twitter.com/dog_rates/status/666050758...	10.0	10.0	None	None	135	...	1	Bernese_mountain_dog	0.651137	True	English_springer	0.263788	True	Greater_Swiss_Mountain_dog	0.016199	True
7864	666049248165822465	2015-11-16 00:24:50	<a href="http://twitter.com/download/iphone" r...	Here we have a 1949 1st generation vulpix. Enj...	https://twitter.com/dog_rates/status/666049248...	5.0	10.0	None	None	110	...	1	miniature_pinscher	0.560311	True	Rottweiler	0.243682	True	Doberman	0.154629	True
7868	666044226329800704	2015-11-16 00:04:52	<a href="http://twitter.com/download/iphone" r...	This is a purebred Piers Morgan. Loves to Netf...	https://twitter.com/dog_rates/status/666044226...	6.0	10.0	None	None	305	...	1	Rhodesian_ridgeback	0.408143	True	redbone	0.360687	True	miniature_pinscher	0.222752	True
7872	666033412701032449	2015-11-15 23:21:54	<a href="http://twitter.com/download/iphone" r...	Here is a very happy pup. Big fan of well-main...	https://twitter.com/dog_rates/status/666033412...	9.0	10.0	None	None	126	...	1	German_shepherd	0.596461	True	malinois	0.138584	True	bloodhound	0.116197	True
7876	666029285002620928	2015-11-15 23:05:30	<a href="http://twitter.com/download/iphone" r...	This is a western brown Mitsubishi terrier. Up...	https://twitter.com/dog_rates/status/666029285...	7.0	10.0	None	None	131	...	1	redbone	0.506826	True	miniature_pinscher	0.074192	True	Rhodesian_ridgeback	0.072010	True
7880	666020888022790149	2015-11-15 22:32:08	<a href="http://twitter.com/download/iphone" r...	Here we have a Japanese Irish Setter. Lost eye...	https://twitter.com/dog_rates/status/666020888...	8.0	10.0	None	None	2529	...	1	Welsh_springer_spaniel	0.465074	True	collie	0.156665	True	Shetland_sheepdog	0.061428	True