logistic_regression_colab.py

import pandas as pd
col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age', 'label']
# load dataset
pima = pd.read_csv("diabetes.csv")

pima.head()

#split dataset in features and target variable
feature_cols = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness','Insulin','BMI','DiabetesPedigreeFunction', 'Age']
Xraw = pima[feature_cols] # Features
y = pima.Outcome # Target variable

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X = scaler.fit_transform(Xraw)

# split X and y into training and testing sets
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.13,random_state=0)

# import the class
from sklearn.linear_model import LogisticRegression

# instantiate the model (using the default parameters)
logreg = LogisticRegression()

# fit the model with data
logreg.fit(X_train,y_train)

#
y_pred=logreg.predict(X_test)

# import the metrics class
from sklearn import metrics
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
cnf_matrix

"""**Print Weight and bias vectors**"""

print('Weight matrix:')
print(logreg.coef_) # returns a matrix of weights (coefficients)

import numpy as np
print('Bias value:')
np.hstack(logreg.intercept_)