From 354a03e71c697367b518d2702c8222e140f75437 Mon Sep 17 00:00:00 2001
From: joaopedrorosadacanesin <jpcanesin@gmail.com>
Date: Fri, 16 Nov 2018 11:54:07 +0100
Subject: [PATCH] MVP almost done
---
.../__pycache__/dataframe.cpython-36.pyc | Bin 1269 -> 1252 bytes
twitterPredictor/twitterCollect/dataframe.py | 3 +-
twitterPredictor/twitterCollect/opinion.py | 36 ++++++++++++++++++
3 files changed, 37 insertions(+), 2 deletions(-)
create mode 100644 twitterPredictor/twitterCollect/opinion.py
diff --git a/twitterPredictor/twitterCollect/__pycache__/dataframe.cpython-36.pyc b/twitterPredictor/twitterCollect/__pycache__/dataframe.cpython-36.pyc
index 1e169cdb07df7a6edb1e6ec52e443e55e2253a02..c9abb0d78d329c2b6221a9c902a1054ffa06b314 100644
GIT binary patch
delta 338
zcmey$`Gk|xn3tDJYT>)+*%LWesPHf{Fr+ioG6FFZ5HkZY3lOuWFxIkF)YLGzFvONj
zyc#7^!;-~N!=A<3%*e=4!wP1zP4;CJH)YS_s9|hotmQ5Nv6z4?9x#g;$l?XFSb!`(
zFbk-=mLJICoII1UPd17<D5N-w)h9DMwfH3y0|UcLW)Q&wBs94uyD(`?E@o0@jG8>1
zX&0l|<RIo=MuW)@m=)c47zLR57`b4O$%wf~0;uN}M|^y4VrE`^{4GA$+}y;x($pN^
z#N?v<JWakRwt~dGl*Hm90iePnkX^SXd$Jhw!}R4P=B5JmP3~q<QW6BovKAC&=9S!H
Z$w*C1DG~!|LJ;DU&$1}88*wm#AOIT!RFD7w
delta 373
zcmaFD`IVE?n3tF9K>xewZ4)_HsE9E#Fr+ioG6FFZ5HkZY3lOuWFxIkFwAC=UFvQkP
zyc(5N!dk<g#n#No$WX(Q#Q<lsg4ygK@j|(9h7`6G))eLx_7skE)>^I-jx5d^#%9J^
zZZL}p$l?LBn1L)_FpCAq;sdi-fh>L?i)(T}W1s9T=Ae+`TdY2r*{Q`ZnHU%tUNVCS
z79gR?J=uy$gY6b;K~ZMj<U}SF##@uyn07HrO?G7NWi*<6o>|d@i;;&>fSHex3kI2t
zn2Th9ns0H$$LA(y=EcWH@ww*aCgzo<=J+Ni7v<+^^4(%9NX$z~EG`lTDl7t78a3IB
v#h4$aFE24S6{v4=1&fk`C`gGA$Uv5i)Wnn`DG(n)NKf9wqR4K{!3cr?8yQ=n
diff --git a/twitterPredictor/twitterCollect/dataframe.py b/twitterPredictor/twitterCollect/dataframe.py
index 1c0ad01..4cd8243 100644
--- a/twitterPredictor/twitterCollect/dataframe.py
+++ b/twitterPredictor/twitterCollect/dataframe.py
@@ -37,8 +37,7 @@ def convert_2_dataframe(data):
hash_list.append("#"+hash.get("text"))
hashtags.append(hash_list)
-
- print(tweet.retweet_count)
+
retweets.append(tweet.retweet_count)
likes.append(tweet.favorite_count)
diff --git a/twitterPredictor/twitterCollect/opinion.py b/twitterPredictor/twitterCollect/opinion.py
new file mode 100644
index 0000000..77714df
--- /dev/null
+++ b/twitterPredictor/twitterCollect/opinion.py
@@ -0,0 +1,36 @@
+from collect_candidate_tweet_activity import *
+from dataframe import *
+from textblob import *
+
+def categorize_tweets(data,neutral_line):
+ pos_tweets = []
+ neu_tweets = []
+ neg_tweets = []
+
+ for item in data["text"]:
+ try:
+ blob = TextBlob(item)
+ blob = blob.translate(to='en')
+ except:
+ blob = TextBlob(item)
+
+ polarity = blob.sentiment.polarity
+ print(blob)
+ print(polarity)
+ if polarity<=neutral_line and polarity >=-neutral_line:
+ neu_tweets.append(item)
+ elif polarity > neutral_line:
+ pos_tweets.append(item)
+ else:
+ neg_tweets.append(item)
+
+ return pos_tweets,neu_tweets,neg_tweets
+
+tweets = get_replies_to_candidate("EmmanuelMacron")
+data = convert_2_dataframe(tweets)
+
+pos_tweets,neu_tweets,neg_tweets = categorize_tweets(data,0.1)
+
+print("Percentage of positive tweets: {}%".format(len(pos_tweets)*100/len(data['text'])))
+print("Percentage of neutral tweets: {}%".format(len(neu_tweets)*100/len(data['text'])))
+print("Percentage de negative tweets: {}%".format(len(neg_tweets)*100/len(data['text'])))
--
GitLab