Sentiment Analysis of Movie Reviews

README.md

@@ -1,9 +1,9 @@
-# Machine Learning from Scratch
+# Machine Learning from Scratch.
 This is the code repository for my [Machine Learning from Scratch youtube playlist](https://www.youtube.com/watch?v=4PHI11lX11I&list=PLP3ANEJKF1TzOz3hwOoRclgRFVi8A76k2)
-## 01 Linear Regression using Least Squares  
+## 01 Linear Regression using Least Squares.  
 [Check out the tutorial video](https://www.youtube.com/watch?v=kR6tBAq16ng&t=2s)
-## 02 Linear Regression using Gradient Descent  
+## 02 Linear Regression using Gradient Descent.  
 [Check out the tutorial video](https://www.youtube.com/watch?v=4PHI11lX11I&t=2s)
 [Check out the medium post](https://towardsdatascience.com/linear-regression-using-gradient-descent-97a6c8700931)
-## 03 Linear Regression in 2 minutes
+## 03 Linear Regression in 2 minutes.
 [Check out the medium post](https://towardsdatascience.com/linear-regression-in-6-lines-of-python-5e1d0cd05b8d)

movie.py

@@ -0,0 +1,70 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sat May 12 00:18:03 2018
+@author: jishn
+"""
+#Code which is used to find sentiment of the viewers.
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Churn_Modelling.csv')
+X = dataset.iloc[:, 3:13].values
+y = dataset.iloc[:, 13].values
+
+# Encoding categorical data
+from sklearn.preprocessing import LabelEncoder, OneHotEncoder
+labelencoder_X_1 = LabelEncoder()
+X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
+labelencoder_X_2 = LabelEncoder()
+X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
+onehotencoder = OneHotEncoder(categorical_features = [1])
+X = onehotencoder.fit_transform(X).toarray()
+X = X[:, 1:]
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+X_train = sc.fit_transform(X_train)
+X_test = sc.transform(X_test)
+
+
+import keras
+from keras.models import Sequential
+from keras.layers import Dense
+
+## used to initialise differnet layers
+classifier=Sequential()
+## adding the first layer init specifies the initial value to the weights closer to 0
+## activation fn is Rectifier
+## here the number of nodes taken is the avg of no of input parameters and output
+## Best method is k cross validation
+classifier.add(Dense(output_dim=6,init='uniform',activation='relu',input_dim=11))
+
+classifier.add(Dense(output_dim=6,init='uniform',activation='relu'))
+
+
+classifier.add(Dense(output_dim=1,init='uniform',activation='sigmoid'))
+
+# Compiling the ANN
+classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
+
+# Fitting the ANN to the Training set
+classifier.fit(X_train, y_train, batch_size = 10, nb_epoch = 100)
+
+# Part 3 - Making the predictions and evaluating the model
+
+# Predicting the Test set results
+y_pred = classifier.predict(X_test)
+y_pred = (y_pred > 0.5)
+
+# Making the Confusion Matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)
+
+print("Accuracy:",((cm[0][0]+cm[1][1])/2000))