loading
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
'''
The following code is for XGBoost
Created by - ANALYTICS VIDHYA
'''

# importing required libraries
import pandas as pd
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score

# read the train and test dataset
train_data = pd.read_csv('train-data.csv')
test_data = pd.read_csv('test-data.csv')

# shape of the dataset
print('Shape of training data :',train_data.shape)
print('Shape of testing data :',test_data.shape)

# Now, we need to predict the missing target variable in the test data
# target variable - Survived

# seperate the independent and target variable on training data
train_x = train_data.drop(columns=['Survived'],axis=1)
train_y = train_data['Survived']

# seperate the independent and target variable on testing data
test_x = test_data.drop(columns=['Survived'],axis=1)
test_y = test_data['Survived']

'''
Create the object of the XGBoost model
You can also add other parameters and test your code here
Some parameters are : max_depth and n_estimators
Documentation of xgboost:

https://xgboost.readthedocs.io/en/latest/
'''
model = XGBClassifier()

# fit the model with the training data
model.fit(train_x,train_y)


# predict the target on the train dataset
predict_train = model.predict(train_x)
print('\nTarget on train data',predict_train) 

# Accuray Score on train dataset
accuracy_train = accuracy_score(train_y,predict_train)
print('\naccuracy_score on train dataset : ', accuracy_train)

# predict the target on the test dataset
predict_test = model.predict(test_x)
print('\nTarget on test data',predict_test) 

# Accuracy Score on test dataset
accuracy_test = accuracy_score(test_y,predict_test)
print('\naccuracy_score on test dataset : ', accuracy_test)