Delete perceptron_code.py

perceptron_code.py

@@ -1,85 +0,0 @@
-import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score, classification_report
-import pickle
-from tensorflow.keras.datasets import imdb
-from tensorflow.keras.preprocessing import sequence
-
-import numpy as np
-
-class Perceptron:
-    def __init__(self, input_size, epochs=100, learning_rate=0.01, activation_function='sigmoid'):
-        self.weights = np.zeros(input_size)  # Remove 1 for the bias term
-        self.bias = 0
-        self.epochs = epochs
-        self.learning_rate = learning_rate
-        self.activation_function = activation_function
-
-    def activate(self, x):
-        if self.activation_function == 'sigmoid':
-            return 1 / (1 + np.exp(-x))
-        elif self.activation_function == 'step':
-            return np.where(x >= 0, 1, 0)
-        else:
-            raise ValueError(f"Unsupported activation function: {self.activation_function}")
-
-    def fit(self, X, y):
-        for epoch in range(self.epochs):
-            for xi, target in zip(X, y):
-                prediction = self.activate(np.dot(xi, self.weights) + self.bias)
-                error = target - prediction
-                self.weights += self.learning_rate * error * xi
-                self.bias += self.learning_rate * error
-
-    def predict(self, X):
-        # Remove the column of ones for the bias term
-        weighted_sum = np.dot(X, self.weights) + self.bias
-        return self.activate(weighted_sum)
-
-
-    def predict(self, X):
-        # Remove the column of ones for the bias term
-        weighted_sum = np.dot(X, self.weights) + self.bias
-        return self.activate(weighted_sum)
-
-
-
-def save_model(perceptron):
-    with open('perceptron_model.pkl', 'wb') as model_file:
-        pickle.dump(perceptron, model_file)
-
-# Load the IMDB dataset
-top_words = 5000
-(X_train, y_train), (X_test, y_test) = imdb.load_data(num_words=top_words)
-
-# Preprocess labels for binary classification
-y_train = np.array(y_train)
-y_test = np.array(y_test)
-y_train = np.where(y_train >= 7, 1, 0)
-y_test = np.where(y_test >= 7, 1, 0)
-
-# Normalize input data
-max_review_length = 500
-X_train = sequence.pad_sequences(X_train, maxlen=max_review_length)
-X_test = sequence.pad_sequences(X_test, maxlen=max_review_length)
-
-# Create and train the Perceptron
-input_size = X_train.shape[1]
-learning_rate = 0.01
-perceptron = Perceptron(input_size=input_size, epochs=10, learning_rate=learning_rate)
-perceptron.fit(X_train, y_train)
-
-# Save the trained model
-save_model(perceptron)
-
-# Make predictions
-pred = perceptron.predict(X_test)
-
-# Assuming pred contains probabilities
-threshold = 0.5
-binary_predictions = (pred > threshold).astype(int)
-
-# Now use binary_predictions for evaluation
-print(f"Accuracy: {accuracy_score(y_test, binary_predictions)}")
-report = classification_report(y_test, binary_predictions, digits=2)
-print(report)