preprocess

app.py

@@ -31,6 +31,33 @@ auth = tw.OAuthHandler(consumer_key, consumer_secret)
 auth.set_access_token(access_token, access_token_secret)
 api = tw.API(auth, wait_on_rate_limit=True)
 
+def preprocess(text):
+    text=text.lower()
+    # remove hyperlinks
+    text = re.sub(r'https?:\/\/.*[\r\n]*', '', text)
+    text = re.sub(r'http?:\/\/.*[\r\n]*', '', text)
+    #Replace &amp, &lt, &gt with &,<,> respectively
+    text=text.replace(r'&amp;?',r'and')
+    text=text.replace(r'&lt;',r'<')
+    text=text.replace(r'&gt;',r'>')
+    #remove hashtag sign
+    #text=re.sub(r"#","",text)   
+    #remove mentions
+    text = re.sub(r"(?:\@)\w+", '', text)
+    #text=re.sub(r"@","",text)
+    #remove non ascii chars
+    text=text.encode("ascii",errors="ignore").decode()
+    #remove some puncts (except . ! ?)
+    text=re.sub(r'[:"#$%&\*+,-/:;<=>@\\^_`{|}~]+','',text)
+    text=re.sub(r'[!]+','!',text)
+    text=re.sub(r'[?]+','?',text)
+    text=re.sub(r'[.]+','.',text)
+    text=re.sub(r"'","",text)
+    text=re.sub(r"\(","",text)
+    text=re.sub(r"\)","",text)
+    text=" ".join(text.split())
+    return text
+
 def highlight_survived(s):
     return ['background-color: red']*len(s) if (s.Sexista == 1) else ['background-color: green']*len(s)
 
@@ -38,6 +65,7 @@ def color_survived(val):
     color = 'red' if val=='Sexista' else 'white'
     return f'background-color: {color}'
 
+
 st.set_page_config(layout="wide")
 st.markdown('<style>body{background-color: Blue;}</style>',unsafe_allow_html=True)