Adding Base Project

Author: Priyansh Gupta

BNIEFinal.txt

@@ -8,8 +8,6 @@
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.naive_bayes import GaussianNB
-from sklearn.naive_bayes import MultinomialNB
-from sklearn.metrics import accuracy_score
 from sklearn import svm
 csvFile=open('newfrequency300.csv', 'rt')
 csvReader=csv.reader(csvFile)
@@ -28,21 +26,17 @@
 x=vectorizer.fit_transform(corpus).toarray()
 result=np.append(x,y,axis=1)
 X=pandas.DataFrame(result)
-#model=GaussianNB()
-model=MultinomialNB()
+model=GaussianNB()
 train = X.sample(frac=0.8, random_state=1)
 test=X.drop(train.index)
 y_train=train[301]
 y_test=test[301]
-print('Training model for Judging/Perception')
 print(train.shape)
 print(test.shape)
 xtrain=train.drop(301,axis=1)
 xtest=test.drop(301,axis=1)
 model.fit(xtrain,y_train)
-print(model)
-print('Accuracy : %f' % accuracy_score(y_true=xtrain[0][:66403],y_pred=xtest[0][:]))
-pickle.dump(model, open('BNPJFinal.txt', 'wb'))
+pickle.dump(model, open('BNPJFinal.sav', 'wb'))
 del result
 
 y=[]
@@ -58,21 +52,17 @@
 x=vectorizer.fit_transform(corpus).toarray()
 result=np.append(x,y,axis=1)
 X=pandas.DataFrame(result)
-#model=GaussianNB()
-model=MultinomialNB()
+model=GaussianNB()
 train = X.sample(frac=0.8, random_state=1)
 test=X.drop(train.index)
 y_train=train[301]
 y_test=test[301]
-print('Training model for Introversion/Extraversion')
 print(train.shape)
 print(test.shape)
 xtrain=train.drop(301,axis=1)
 xtest=test.drop(301,axis=1)
 model.fit(xtrain,y_train)
-print(model)
-print('Accuracy : %f' % accuracy_score(y_true=xtrain[0][:85570],y_pred=xtest[0][:]))
-pickle.dump(model, open('BNIEFinal.txt', 'wb'))
+pickle.dump(model, open('BNIEFinal.sav', 'wb'))
 del result
 
 y=[]
@@ -88,21 +78,17 @@
 x=vectorizer.fit_transform(corpus).toarray()
 result=np.append(x,y,axis=1)
 X=pandas.DataFrame(result)
-#model=GaussianNB()
-model=MultinomialNB()
+model=GaussianNB()
 train = X.sample(frac=0.8, random_state=1)
 test=X.drop(train.index)
 y_train=train[301]
 y_test=test[301]
-print('Training model for Thinking/Feeling')
 print(train.shape)
 print(test.shape)
 xtrain=train.drop(301,axis=1)
 xtest=test.drop(301,axis=1)
 model.fit(xtrain,y_train)
-print(model)
-print('Accuracy : %f' % accuracy_score(y_true=xtrain[0][:64000],y_pred=xtest[0][:]))
-pickle.dump(model, open('BNTFFinal.txt', 'wb'))
+pickle.dump(model, open('BNTFFinal.sav', 'wb'))
 del result
 
 y=[]
@@ -118,18 +104,14 @@
 x=vectorizer.fit_transform(corpus).toarray()
 result=np.append(x,y,axis=1)
 X=pandas.DataFrame(result)
-#model=GaussianNB()
-model=MultinomialNB()
+model=GaussianNB()
 train = X.sample(frac=0.8, random_state=1)
 test=X.drop(train.index)
 y_train=train[301]
 y_test=test[301]
-print('Training model for Sensing/iNtuition')
 print(train.shape)
 print(test.shape)
 xtrain=train.drop(301,axis=1)
 xtest=test.drop(301,axis=1)
 model.fit(xtrain,y_train)
-print(model)
-print('Accuracy : %f' % accuracy_score(y_true=xtrain[0][:47135],y_pred=xtest[0][:]))
-pickle.dump(model, open('BNSNFinal.txt', 'wb'))
+pickle.dump(model, open('BNSNFinal.sav', 'wb'))

BNPJFinal.txt

@@ -1,3 +1,4 @@
+#  -*- coding: utf-8 -*-
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
 from nltk.stem import *
@@ -18,10 +19,10 @@
 from sklearn.feature_extraction.text import TfidfVectorizer
 from collections import Counter
 
-ckey='M9cjHbuSsAFkUZWPrbhY2Q0kL'
-csecret='aYpMuByAZWZoouhqHEjs3BqUNhwF9NfoEHodGk8nBUdOpBJCgR'
-atoken='994417184322433025-TAGgZ6on9CY8Sn6jyfjJ4giFx8h2jIh'
-asecret='tUItYxsghg0m4kw6QqmiKLVkQzLeNN2r6ZzLSFrvQSARQ'
+ckey='...'
+csecret='...'
+atoken='...'
+asecret='...'
 auth=tweepy.OAuthHandler(ckey, csecret)
 auth.set_access_token(atoken, asecret)
 api=tweepy.API(auth)
@@ -125,7 +126,7 @@ def getTweets(user):
 with open('user.csv','rt') as f:
 	csvReader=csv.reader(f)
 	tweetList=[rows[0] for rows in csvReader]
-#os.remove('user.csv')
+os.remove('user.csv')
 with open('newfrequency300.csv','rt') as f:
 	csvReader=csv.reader(f)
 	mydict={rows[1]: int(rows[0]) for rows in csvReader}
@@ -135,10 +136,10 @@ def getTweets(user):
 df=pd.DataFrame(x)
 
 
-model_IE = pickle.load(open("BNIEFinal.txt", 'rb'))
-model_SN = pickle.load(open("BNSNFinal.txt", 'rb'))
-model_TF = pickle.load(open('BNTFFinal.txt', 'rb'))
-model_PJ = pickle.load(open('BNPJFinal.txt', 'rb'))
+model_IE = pickle.load(open("BNIEFinal.sav", 'rb'))
+model_SN = pickle.load(open("BNSNFinal.sav", 'rb'))
+model_TF = pickle.load(open('BNTFFinal.sav', 'rb'))
+model_PJ = pickle.load(open('BNPJFinal.sav', 'rb'))
 
 answer=[]
 IE=model_IE.predict(df)
@@ -179,4 +180,4 @@ def getTweets(user):
 else:
 	answer.append("J")
 mbti="".join(answer)
-print(mbti)
+print(mbti)