import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
pd.options.mode.chained_assignment = None  # default='warn'

def reading_data(path):
    return pd.read_csv(path)


def prepare_data(df):
    df['isExpensiveFare'] = df['fare'] > 150
    df['isAdult'] = df['age'] > 18
    return df

if __name__ == '__main__':
    # Reading in Data
    path = 'data/titanic.csv'
    C = 100.0
    penalty = 'l2'

    df = reading_data(path)
    df = prepare_data(df)

    X = df[['isExpensiveFare', 'isAdult', 'parch']]
    Y = df['survived']
    train_x,test_x,train_y,test_y = train_test_split(X,Y,random_state=42,test_size=.5)

    # Define Model
    model = LogisticRegression(C=C, penalty=penalty)
    print("Training on {} rows".format(len(train_x)))
    model.fit(train_x,train_y)

    preds = model.predict(test_x)
    score = accuracy_score(test_y,preds)
    print("Accuracy : {}%".format(score))