Adding Log Reg functions

CNN.py

@@ -21,7 +21,14 @@
 import re
 from nltk.corpus import stopwords
 from numpy import array
+
+#sklearn
 from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.linear_model import LogisticRegression
+
+
+
 
 
 # Snowflake Credentials from env variables #
@@ -30,6 +37,7 @@
 ACCOUNT = os.getenv('SNOWACCT')
 USER = os.getenv('SNOWUSER')
 
+
 # Connection Manager for Snowflake Instance #
 con = snowflake.connector.connect(
     user=USER,
@@ -48,3 +56,42 @@
 
 df = cur.fetch_pandas_all()
 
+# Start of Convolutional Models #
+
+# Yelp Log Reg for baseline test #
+df_yelp = df[df['source'] == 'yelp']
+
+sentences = df_yelp['sentence'].values
+
+y = df_yelp['label'].values
+sentences_train, sentences_test, y_train, y_test = train_test_split(sentences, y, test_size=0.25, random_state=1000)
+
+vectorizer = CountVectorizer()
+vectorizer.fit(sentences_train)
+
+X_train = vectorizer.transform(sentences_train)
+X_test = vectorizer.transform(sentences_test)
+
+classifier = LogisticRegression()
+classifier.fit(X_train, y_train)
+score = classifier.score(X_test, y_test)
+
+print('Accuracy of Log Reg: ', score)
+
+# Log Reg for each unique source in dataframe #
+for source in df['source'].unique():
+    df_source = df[df['source'] == source]
+    sentences = df_source['sentence'].values
+    y = df_source['label'].values
+
+    sentences_train, sentences_test, y_train, y_test = train_test_split(sentences, y, test_size=0.25, random_state=1000)
+
+    vectorizer = CountVectorizer()
+    vectorizer.fit(sentences_train)
+    X_train = vectorizer.transform(sentences_train)
+    X_test  = vectorizer.transform(sentences_test)
+
+    classifier = LogisticRegression()
+    classifier.fit(X_train, y_train)
+    score = classifier.score(X_test, y_test)
+    print('Accuracy for {} data: {:.4f}'.format(source, score))