PankajMehar

import pandas as pd
import numpy as np
import random as rnd
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
import random as rnd

## Code courtsey: Manav Sehgal (https://www.kaggle.com/startupsci)
## Link to Original Code: https://www.kaggle.com/startupsci/titanic-data-science-solutions

PankajMehar

train_df = pd.read_csv(train)
test_df = pd.read_csv(test)

PankajMehar

train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)

PankajMehar

import pandas as pd
import numpy as np
import random as rnd
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
import random as rnd

PankajMehar

train = pd.get_dummies(train)
test = pd.get_dummies(test)
    

PankajMehar

# x contains of features
X = train.iloc[:, 1:]
# y is the target
y = train.iloc[:, 0]
    
  
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state= 50)

PankajMehar

def gridfunc(classifier, parameter, X, y):
    clf = classifier
    parameters = parameter
    acc_scorer = make_scorer(accuracy_score)
    # Run the grid search
    grid_obj = GridSearchCV(clf, parameters, scoring=acc_scorer)
    grid_obj = grid_obj.fit(X_train, y_train)
    
    return grid_obj
  

PankajMehar

y_predict = clf.predict(X_test)
y_predict

from sklearn import metrics
from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_predict)

0.84328358208955223

PankajMehar

Variable	Definition	Key
survival 	Survival 	0 = No, 1 = Yes
pclass 	Ticket class 	1 = 1st, 2 = 2nd, 3 = 3rd
sex 	Sex 	
Age 	Age in years 	
sibsp 	# of siblings / spouses aboard the Titanic 	
parch 	# of parents / children aboard the Titanic 	
ticket 	Ticket number 	
fare 	Passenger fare 	
cabin 	Cabin number 	

PankajMehar

train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)