prodigy_task_3.py

# -*- coding: utf-8 -*-
"""Prodigy_task_3.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1rN6byQUe2Zp72hPQyZPo4F7lthBv_FUf

# **Prodigy DS Internship Task 3**

## Making a decision tree classifier

## **Import necessary libraries**
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, accuracy_score
from sklearn import tree

"""# **Loading of data**"""

d=pd.read_csv('/content/bank data - bank-full - bank data - bank-full (1).csv', header=0, sep=',');
df=pd.DataFrame(data=d)
df.head

"""# **Dropping the empty columns**"""

df.dropna(axis=0,inplace=True)
df

df.info()

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
df['job'] = le.fit_transform(df['job'])
df['job']=df['job'].astype(float)

df['marital'] = le.fit_transform(df['marital'])
df['marital']=df['marital'].astype(float)

df['education'] = le.fit_transform(df['education'])
df['education']=df['education'].astype(float)

df['poutcome'] = le.fit_transform(df['poutcome'])
df['poutcome']=df['poutcome'].astype(float)

df['month'] = le.fit_transform(df['month'])
df['month']=df['month'].astype(float)

df['contact'] = le.fit_transform(df['contact'])
df['contact']=df['contact'].astype(float)

df['housing'] = le.fit_transform(df['housing'])
df['housing']=df['housing'].astype(float)

df['default'] = le.fit_transform(df['default'])
df['default']=df['default'].astype(float)

df['loan'] = le.fit_transform(df['loan'])
df['loan']=df['loan'].astype(float)

df.info()

"""# **Defining X and Y for test and train split**"""

X=df.values[:,1:16]
print('These are the X values')
print(X)

Y=df.values[:,16]
print('These are the Y values')
print(Y)

"""# **Test-Train split**"""

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=123, shuffle=True)

"""# **Model Fitting**"""

mytree=DecisionTreeClassifier(criterion='gini',max_depth=4)
mytree.fit(X_train,Y_train)
pred=mytree.predict(X_test)
print(classification_report(Y_test, pred))
print("Our model has achieved an accuracy of ", accuracy_score(Y_test, pred)*100, "%", sep="")

from sklearn import tree
plt.figure(figsize=(25, 25))
tree.plot_tree(mytree, rounded=False,filled=True,fontsize=10)
plt.show()