import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn import tree

from sklearn.metrics import accuracy_score

# Figures inline and set visualization style

%matplotlib inline

sns.set()

df = pd.read_csv('https://raw.githubusercontent.com/hugobowne/deep-learning-from-scratch-pytorch/master/data/train.csv')

# View first lines of training data

df.head(n=4)

df.info()

df.describe()

from sklearn.model_selection import train_test_split

df_train, df_test, y_train, y_test = train_test_split(

    df.drop('Survived', axis=1), df[['Survived']], test_size=0.33, random_state=42, stratify=df[['Survived']])

df_train['Survived'] = y_train

sns.countplot(x='Survived', data=df_train);

df_test['Survived'] = 0

pred_diff = y_test['Survived'] - df_test['Survived'].array

accuracy = 1 - sum(pred_diff)/len(pred_diff)

print(accuracy)

df['Age'] = df.Age.fillna(df.Age.median())

df['Fare'] = df.Fare.fillna(df.Fare.median())

df.info()

df = pd.get_dummies(df, columns=['Sex'], drop_first=True)

df = df[['Sex_male', 'Fare', 'Age','Pclass', 'SibSp','Survived']]

df.head()

df_train, df_test, y_train, y_test = train_test_split(

    df.drop('Survived', axis=1), df[['Survived']], test_size=0.33, random_state=41, stratify=df[['Survived']])

clf = tree.DecisionTreeClassifier(max_depth=3)

clf.fit(df_train, y_train)