Machine Learning Project – Titanic Movie in Decision Tree Part 2

Program 1

import pandas as pd
import numpy as np
from sklearn import tree
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split


df_titanic=pd.read_csv("D://scikit_data/titanicData/titanic.csv")


df_titanic


df_titanic.shape


df_titanic.info()


# Find Missing values
df_titanic.isnull().sum()


df_titanic=df_titanic.dropna()


df_titanic.isnull().sum()


df_titanic.shape


df_titanic


# Label Encoding Process
le=LabelEncoder()
df_titanic['Sex_new']=le.fit_transform(df_titanic['Sex'])


df_titanic


df_titanic=df_titanic.drop('Sex',axis='columns')


df_titanic


# Independed Variables
df_ind=df_titanic.drop('Survived',axis='columns')


df_ind


# Depended Variables
df_dep=df_titanic.drop(['Pclass','Age','Fare','Sex_new'],axis='columns')


df_dep


x=df_ind
y=df_dep
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)


# x_train--> Training Independed variable
# x_test--> Test Independed variable
#y_train--> Training Depended variable
#y_test--> Testing Depended variable



len(x_train)


len(x_test)


len(y_train)


len(y_test)


# Model Creating Process
model=tree.DecisionTreeClassifier()

model.fit(x_train,y_train)


y_pred_train=model.predict(x_train)


y_pred_train


from sklearn.metrics import accuracy_score


data_acc=accuracy_score(y_pred_train,y_train)


data_acc


y_pred_test=model.predict(x_test)


y_pred_test


data_acc=accuracy_score(y_pred_test,y_test)


data_acc


model.predict([[1,1,54,51.8625]])