finished analysis

analysis.py

@@ -23,7 +23,7 @@ def overall_sentiment(text):
  
     if percent_sentiment['pos'] < 0.1:
         if percent_sentiment['pos']-percent_sentiment['neg'] <= 0 or percent_sentiment['compound'] <= -0.5: # The "=" makes it better
-            print("Sentence overall rated as positive")
+            print("Sentence overall rated as negative")
             print("\n")
            #print("Negative")
             return "Negative"
@@ -36,27 +36,27 @@ def overall_sentiment(text):
     
 
 
-pos_count = 0
-pos_correct = 0
+# pos_count = 0
+# pos_correct = 0
 
-file_positive = open("positive.txt","r")
-file_positive_lines = file_positive.readlines()
-for line in file_positive_lines:
-    sentiment = overall_sentiment(line)
-    if sentiment == "Positive":
-            pos_correct += 1
-    pos_count += 1
+# file_positive = open("positive.txt","r")
+# file_positive_lines = file_positive.readlines()
+# for line in file_positive_lines:
+#     sentiment = overall_sentiment(line)
+#     if sentiment == "Positive":
+#             pos_correct += 1
+#     pos_count += 1
 
-neg_count = 0
-neg_correct = 0
+# neg_count = 0
+# neg_correct = 0
 
-file_negative = open("negative.txt","r")
-file_negative_lines = file_negative.readlines()
-for line in file_negative_lines:
-    sentiment = overall_sentiment(line)
-    if sentiment == "Negative":
-        neg_correct += 1
-    neg_count += 1
+# file_negative = open("negative.txt","r")
+# file_negative_lines = file_negative.readlines()
+# for line in file_negative_lines:
+#     sentiment = overall_sentiment(line)
+#     if sentiment == "Negative":
+#         neg_correct += 1
+#     neg_count += 1
 
-print("Positive accuracy using vader= {}% via {} samples".format(pos_correct/pos_count*100.0, pos_count))
-print("Negative accuracy using vader= {}% via {} samples".format(neg_correct/neg_count*100.0, neg_count))
+# print("Positive accuracy using vader= {}% via {} samples".format(pos_correct/pos_count*100.0, pos_count))
+# print("Negative accuracy using vader= {}% via {} samples".format(neg_correct/neg_count*100.0, neg_count))

twitter.py

@@ -7,9 +7,17 @@ import csv
 import re 
 import string
 import preprocessor as p
- 
+import analysis
+import emoji
+
+# Remove Emojis
+def give_emoji_free_text(text):
+    allchars = [str for str in text]
+    emoji_list = [c for c in allchars if c in emoji.UNICODE_EMOJI]
+    clean_text = ' '.join([str for str in text.split() if not any(i in str for i in emoji_list)])
+
+    return clean_text
 
- 
 auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
 auth.set_access_token(access_key, access_secret)
  
@@ -19,8 +27,10 @@ api = tweepy.API(auth,wait_on_rate_limit=True)
 search_words = "#wildfires"      # enter your words
 new_search = search_words + " -filter:retweets"
 
-for tweets in api.search_tweets(q="iphone", lang="en", count=100, since_id=0):
-    print(tweets.text.encode('utf-8'))
+for tweets in api.search_tweets(q=new_search, lang="en", count=100, since_id=0):
+    print(tweets.text)
+    text = give_emoji_free_text(text=tweets.text)
+    analysis.overall_sentiment(text)
 # #for tweet in tweepy.Cursor(api.search_tweets,q=new_search,count=100,
 #                            lang="en",
 #                            since_id=0).items():