logistic_regression.py

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

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1i30kWyzkd0ejzBAVtz5UMOwNWV6GVqoe
"""

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.naive_bayes import GaussianNB, MultinomialNB
from sklearn.metrics import mean_squared_error, r2_score, classification_report,confusion_matrix, accuracy_score

"""### **Simple Logistic Regression**"""

#Load the data set
data = sns.load_dataset("iris")
#Prepare the training set

# X = feature values, all the columns except the last column
X = data.iloc[:, :-1]# or data.loc[:,'sepal_length':'petal_width']

# y = target values, last column of the data frame
y = data.iloc[:, -1]# or data.loc[:,'species']
data.head()

# Plot the relation of each feature with each species

plt.xlabel('Features')
plt.ylabel('Species')

pltX = data.loc[:, 'sepal_length']
pltY = data.loc[:,'species']
plt.scatter(pltX, pltY, color='blue', label='sepal_length')

pltX = data.loc[:, 'sepal_width']
pltY = data.loc[:,'species']
plt.scatter(pltX, pltY, color='green', label='sepal_width')

pltX = data.loc[:, 'petal_length']
pltY = data.loc[:,'species']
plt.scatter(pltX, pltY, color='red', label='petal_length')

pltX = data.loc[:, 'petal_width']
pltY = data.loc[:,'species']
plt.scatter(pltX, pltY, color='black', label='petal_width')

plt.legend(loc=4, prop={'size':8})
plt.show()

#Split the data into 80% training and 20% testing
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

#Train the model
model = LogisticRegression()
model.fit(x_train, y_train) #Training the model

#Test the model
predictions = model.predict(x_test)
print(predictions)

#Check precision, recall, f1-score
print( classification_report(y_test, predictions) )

print( accuracy_score(y_test, predictions))

classifier = MultinomialNB()
classifier.fit(x_train, y_train)

#Print the predictions
pred = classifier.predict(x_train)
print(classification_report(y_train ,pred ))
print('Confusion Matrix: \n',confusion_matrix(y_train,pred))
print()
print('Accuracy: ', accuracy_score(y_train,pred))