Scribd
Upload
6 views

Logistic Regression

Uploaded by

Belete Siyum
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
6 views

Logistic Regression

Uploaded by

Belete Siyum
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

# Import necessary libraries for data manipulation

import pandas as pd # Pandas for handling and manipulating data


pd.set_option('display.max_columns', None) # Ensures that all columns are
displayed when viewing the data

# Import libraries for machine learning and model evaluation


from sklearn.model_selection import train_test_split # For splitting data into
training and testing sets
from sklearn.linear_model import LogisticRegression # Logistic Regression model
for binary classification
from sklearn.metrics import classification_report # For generating a detailed
classification report

# Load CSV file from Google Drive into a DataFrame


df = pd.read_csv('/content/drive/My Drive/logisticDS.csv', index_col=0) # Update
path for Google Drive

# Display the first few rows and summary of the DataFrame to understand its
structure
print(df.head()) # Shows the first five rows of the dataset
print(df.info()) # Provides a summary of the dataset, including columns and data
types

# Drop unnecessary column


df = df.drop('Unnamed: 32', axis=1) # Removes the extra column ('Unnamed: 32')
that may contain only NaN values

# Select columns for model input


cols = [
'diagnosis',
'radius_mean',
'texture_mean',
'area_mean',
'smoothness_mean',
'compactness_mean',
'concavity_mean',
'concave points_mean',
'symmetry_mean',
'fractal_dimension_mean'
]

# Assign selected columns to x and y variables


x = df[cols] # Select the columns needed for the model
x = x.drop("diagnosis", axis=1) # Remove 'diagnosis' column from x (features) as
it will be used as the target variable
y = df["diagnosis"] # Target variable 'diagnosis' for predicting

# Display the features and target variables to verify correctness


print(x) # Display features
print(y) # Display target

# Split dataset into training (70%) and testing sets (30%)


x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)

# Initialize and fit the Logistic Regression model


model = LogisticRegression()
logistic_fit = model.fit(x_train, y_train) # Train the model using training data

# Predict diagnosis values using the test dataset


predictions = logistic_fit.predict(x_test) # Make predictions on test data
print(predictions[1:10]) # Display a sample of predictions (from index 1 to 9)

# Model accuracy score on the test set


print("Model Accuracy:", model.score(x_test, y_test)) # Provides a score for model
accuracy

# Generate a detailed classification report for evaluation


print(classification_report(y_test, predictions)) # Displays precision, recall,
F1-score, and support for each class

You might also like