Classifiers/RandomForestClassification.py
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 12 22:17:22 2017
@author: Nilay Pathak
"""
# Importing the libraries
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('../titanic_data.csv')
X = dataset.iloc[:, [2,4,5,6,9]].values
y = dataset.iloc[:, 1].values
from sklearn.preprocessing import LabelEncoder
labelencoder_X = LabelEncoder()
X[:, 1] = labelencoder_X.fit_transform(X[:, 1])
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0)
imputer = imputer.fit(X)
X = imputer.transform(X)
# 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 =0.1,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)
# Fitting Random Forest Classification to the Training set
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)