Random Forest and decision Tree the Pythonic way¶
Soumil Nitin Shah¶
Bachelor in Electronic Engineering | Masters in Electrical Engineering | Master in Computer Engineering |
- Website : https://soumilshah.herokuapp.com
- Github: https://github.com/soumilshah1995
- Linkedin: https://www.linkedin.com/in/shah-soumil/
- Blog: https://soumilshah1995.blogspot.com/
- Youtube : https://www.youtube.com/channel/UC_eOodxvwS_H7x2uLQa-svw?view_as=subscriber
- Facebook Page : https://www.facebook.com/soumilshah1995/
- Email : shahsoumil519@gmail.com
- projects : https://soumilshah.herokuapp.com/project
Hello! I’m Soumil Nitin Shah, a Software and Hardware Developer based in New York City. I have completed by Bachelor in Electronic Engineering and my Double master’s in Computer and Electrical Engineering. I Develop Python Based Cross Platform Desktop Application , Webpages , Software, REST API, Database and much more I have more than 2 Years of Experience in Python
Decision Tree¶
In [65]:
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
import scikitplot as skplt
class NN():
def __init__(self, max_iter=150):
self.max_iter=max_iter
self.X_Train, self.X_Test, self.Y_Train, self.Y_Test = self.preprocess
self.model = self.create_model
@property
def preprocess(self):
# Read the Dataset
df = pd.read_csv('loan_data.csv')
# convert the column purpose which is Categorical into Numbers
final_data = pd.get_dummies(df, columns=["purpose"], drop_first=True)
X_Data = final_data[['int.rate', 'installment', 'log.annual.inc', 'dti',
'fico', 'days.with.cr.line', 'revol.bal', 'revol.util',
'inq.last.6mths', 'delinq.2yrs', 'pub.rec', 'not.fully.paid',
'purpose_credit_card', 'purpose_debt_consolidation',
'purpose_educational', 'purpose_home_improvement',
'purpose_major_purchase', 'purpose_small_business']]
Y_Data = final_data ['credit.policy']
X_Train, X_Test, Y_Train, Y_Test = train_test_split(X_Data, Y_Data, test_size=0.4, random_state=101)
return X_Train, X_Test, Y_Train, Y_Test
@property
def create_model(self):
"""
return : Model Object
"""
model = DecisionTreeClassifier()
return model
@property
def train(self):
"""
return None Train the Model
"""
self.model.fit(self.X_Train, self.Y_Train)
@property
def test(self):
"""
return pred [Array ]
return coef_ [array]
return intercept_ [array]
"""
pred = self.model.predict(self.X_Test)
return pred
@property
def download_report(self):
"""
return confusion matrix
return classification report
return plots the confusion matrix
"""
pred = self.test
report = classification_report(self.Y_Test, pred)
matrix = confusion_matrix(self.Y_Test, pred)
skplt.metrics.plot_confusion_matrix(self.Y_Test,
pred,
figsize=(6,6),
title="Confusion Matrix")
return report, matrix
@property
def plot(self):
pass
In [69]:
neural = NN()
neural.train
pred = neural.test
report, matrix = neural.download_report
print(report)
print(matrix)
Random Forest¶
In [67]:
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
import scikitplot as skplt
class NN():
def __init__(self, max_iter=150):
self.max_iter=max_iter
self.X_Train, self.X_Test, self.Y_Train, self.Y_Test = self.preprocess
self.model = self.create_model
@property
def preprocess(self):
# Read the Dataset
df = pd.read_csv('loan_data.csv')
# convert the column purpose which is Categorical into Numbers
final_data = pd.get_dummies(df, columns=["purpose"], drop_first=True)
X_Data = final_data[['int.rate', 'installment', 'log.annual.inc', 'dti',
'fico', 'days.with.cr.line', 'revol.bal', 'revol.util',
'inq.last.6mths', 'delinq.2yrs', 'pub.rec', 'not.fully.paid',
'purpose_credit_card', 'purpose_debt_consolidation',
'purpose_educational', 'purpose_home_improvement',
'purpose_major_purchase', 'purpose_small_business']]
Y_Data = final_data ['credit.policy']
X_Train, X_Test, Y_Train, Y_Test = train_test_split(X_Data, Y_Data, test_size=0.4, random_state=101)
return X_Train, X_Test, Y_Train, Y_Test
@property
def create_model(self):
"""
return : Model Object
"""
model = RandomForestClassifier()
return model
@property
def train(self):
"""
return None Train the Model
"""
self.model.fit(self.X_Train, self.Y_Train)
@property
def test(self):
"""
return pred [Array ]
return coef_ [array]
return intercept_ [array]
"""
pred = self.model.predict(self.X_Test)
return pred
@property
def download_report(self):
"""
return confusion matrix
return classification report
return plots the confusion matrix
"""
pred = self.test
report = classification_report(self.Y_Test, pred)
matrix = confusion_matrix(self.Y_Test, pred)
skplt.metrics.plot_confusion_matrix(self.Y_Test,
pred,
figsize=(6,6),
title="Confusion Matrix")
return report, matrix
@property
def plot(self):
pass
neural = NN()
neural.train
pred = neural.test
report, matrix = neural.download_report
print(report)
print(matrix)
No comments:
Post a Comment