check it

[ItsMyPain]

https://www.kaggle.com/code/vasanth03/cat-or-dog-classification-sklearn-and-pytorch

[elfeliza]

python = ">=3.9,<3.13" numpy = "^1.26.0" pandas = "^2.1.1" torch = { url = "https://download.pytorch.org/whl/cpu/torch-2.1.0%2Bcpu-cp39-cp39-linux_x86_64.whl"}

[elfeliza]

https://www.kdnuggets.com/2022/04/logistic-regression-classification.html

[elfeliza]

import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from math import exp

Source of dataset - https://www.kaggle.com/rakeshrau/social-network-ads

!wget "https://drive.google.com/uc?id=15WAD9_4CpUK6EWmgWVXU8YMnyYLKQvW8&export=download" -O data.csv -q# Load the dataset

data = pd.read_csv("data.csv") data.head(10)

X_train, X_test, y_train, y_test = train_test_split(data['Age'], data['Purchased'], test_size=0.20)

Building the Logistic Regression model

Normalising the data

def normalize(X): return X - X.mean()

Make predictions

def predict(X, b0, b1): return np.array([1 / (1 + exp(-1b0 + -1b1*x)) for x in X])

The model

def logistic_regression(X, Y):

X = normalize(X)

Initializing variables

b0 = 0 b1 = 0 L = 0.001 epochs = 300

for epoch in range(epochs): y_pred = predict(X, b0, b1) D_b0 = -2 sum((Y - y_pred) y_pred (1 - y_pred)) # Loss wrt b0 D_b1 = -2 sum(X (Y - y_pred) y_pred * (1 - y_pred)) # Loss wrt b1

Update b0 and b1

  b0 = b0 - L * D_b0
  b1 = b1 - L * D_b1

  return b0, b1

Training the Model

b0, b1 = logistic_regression(X_train, y_train)# Making predictions and setting a thresholdX_test_norm = normalize(X_test) y_pred = predict(X_test_norm, b0, b1) y_pred = [1 if p >= 0.5 else 0 for p in y_pred]

Plotting the data

plt.scatter(X_test, y_test) plt.scatter(X_test, y_pred, c="red") plt.show()# Calculating the accuracy accuracy = 0 for i in range(len(y_pred)): if y_pred[i] == y_test.iloc[i]: accuracy += 1 print(f"Accuracy = {accuracy / len(y_pred)}")

[elfeliza]

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split 
from math import exp
# Source of dataset - https://www.kaggle.com/rakeshrau/social-network-ads
# !wget "https://drive.google.com/uc?id=15WAD9_4CpUK6EWmgWVXU8YMnyYLKQvW8&export=download" -O data.csv -q# Load the dataset
data = pd.read_csv("data.csv")
data.head(10)

X_train, X_test, y_train, y_test = train_test_split(data['Age'], data['Purchased'], test_size=0.20)

# Building the Logistic Regression model

# Normalising the data
def normalize(X):
  return X - X.mean()

# Make predictions
def predict(X, b0, b1):
  return np.array([1 / (1 + exp(-1*b0 + -1*b1*x)) for x in X])

# The model
def logistic_regression(X, Y):

   X = normalize(X)

   # Initializing variables
   b0 = 0
   b1 = 0
   L = 0.001
   epochs = 300

   for epoch in range(epochs):
      y_pred = predict(X, b0, b1)
      D_b0 = -2 * sum((Y - y_pred) * y_pred * (1 - y_pred)) # Loss wrt b0
      D_b1 = -2 * sum(X * (Y - y_pred) * y_pred * (1 - y_pred)) # Loss wrt b1
      # Update b0 and b1
      b0 = b0 - L * D_b0
      b1 = b1 - L * D_b1

      return b0, b1

   # Training the Model
b0, b1 = logistic_regression(X_train, y_train)# Making predictions and setting a thresholdX_test_norm = normalize(X_test)
y_pred = predict(X_test_norm, b0, b1)
y_pred = [1 if p >= 0.5 else 0 for p in y_pred]
# Plotting the data
plt.scatter(X_test, y_test)
plt.scatter(X_test, y_pred, c="red")
plt.show()# Calculating the accuracy
accuracy = 0
for i in range(len(y_pred)):
    if y_pred[i] == y_test.iloc[i]:
        accuracy += 1
        print(f"Accuracy = {accuracy / len(y_pred)}")