#10 Titanic Survival Model.py

# A.Importing Libraries -->
import pandas as pd
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

# Models Used -->
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.svm import SVC

# B.Setting Up Dataframe -->
train_data = pd.read_csv('data/train.csv')
test_data = pd.read_csv('data/test.csv')
result = pd.read_csv('data/my_submission.csv')

women = train_data.loc[train_data.Sex == 'female']["Survived"]
rate_women = sum(women)/len(women)
men = train_data.loc[train_data.Sex =='male']["Survived"]
rate_men = sum(men)/len(men)

# C.Setting Up Training Testing Data -->
y_train = train_data["Survived"]
y_test = result['Survived']

features = ["Pclass","Sex", "SibSp","Parch"]
X_train = pd.get_dummies(train_data[features])
X_test = pd.get_dummies(test_data[features])

# D.Training Models On Data -->

# 1.Decision Tree Classifier -->
dtc = make_pipeline(StandardScaler(), DecisionTreeClassifier(random_state=0))
dtc.fit(X_train,y_train)

# 2.Random Forest Classifier -->
rf =  make_pipeline(RandomForestClassifier(n_estimators=100, max_depth=5, random_state=0))
rf.fit(X_train, y_train)

# 3.Gradient boosting regressor -->
gbc = make_pipeline(GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0))
gbc.fit(X_train, y_train)

# 4.Support Vector classification -->
svc = make_pipeline(SVC(gamma="auto"))
svc.fit(X_train,y_train)

# E.Analysing Results -->

# 1.Decision Tree Classifier -->
print("-----------------------------------")
print('Decision Tree Classifier')
print('Accuracy Score: {:,.2f}'.format(dtc.score(X_test, y_test)))
print()
print(classification_report(y_test, dtc.predict(X_test)))
print()
print('confusion_matrix: \n {}'.format(confusion_matrix(y_test, dtc.predict(X_test))))
print()
print("-----------------------------------")

# 2.Random Forest Classifier -->
print("-----------------------------------")
print('Random Forest Classification')
print('Accuracy Score: {:,.2f}'.format(rf.score(X_test,y_test)))
print()
print(classification_report(y_test, rf.predict(X_test)))
print()
print('confusion_matrix: \n {}'.format(confusion_matrix(y_test,rf.predict(X_test))))
print()
print("-----------------------------------")

# 3.Gradient Boosted regressor -->
print("-----------------------------------")
print('Gradient Booster')
print('Accuracy Score: {:,.2f}'.format(gbc.score(X_test, y_test)))
print()
print(classification_report(y_test, gbc.predict(X_test)))
print()
print('confusion_matrix: \n {}'.format(confusion_matrix(y_test, gbc.predict(X_test))))
print()
print("-----------------------------------")

# 4.Support Vector classification -->
print("-----------------------------------")
print('Support Vector Machine')
print('Accuracy score: {:,.2f}'.format(svc.score(X_test,y_test)))
print()
print(classification_report(y_test, svc.predict(X_test)))
print()
print('confusion_matrix: \n {}'.format(confusion_matrix(y_test,svc.predict(X_test))))
print()
print("-----------------------------------")