Classification-App / Spam_dnn.py
SandraPK's picture
Upload 24 files
a4a5dbc
raw
history blame
3.03 kB
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, Flatten, Dense
import pickle
# Load the dataset
txt_file_path = 'SMSSpamCollection.txt'
# Initialize empty lists to store labels and messages
labels = []
messages = []
# Read the text file line by line and extract labels and messages
try:
with open(txt_file_path, 'r', encoding='utf-8') as file:
for line in file:
parts = line.strip().split('\t')
if len(parts) == 2:
label, message = parts
labels.append(label)
messages.append(message)
# Create a DataFrame from the lists
dataset = pd.DataFrame({'label': labels, 'message': messages})
# Print the first few rows of the dataframe to check if data is loaded successfully
print(dataset.head())
except Exception as e:
print(f"Error reading text file: {e}")
# Assuming your dataset has 'label' and 'message' columns
X = dataset['message'].values
y = dataset['label'].map({'spam': 1, 'ham': 0}).values
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Tokenize the text data
max_words = 10000
tokenizer = Tokenizer(num_words=max_words, oov_token='<OOV>')
tokenizer.fit_on_texts(X_train)
sequences_train = tokenizer.texts_to_sequences(X_train)
sequences_test = tokenizer.texts_to_sequences(X_test)
# Pad sequences to a fixed length
max_sequence_length = 200
X_train_padded = pad_sequences(sequences_train, maxlen=max_sequence_length, padding='post')
X_test_padded = pad_sequences(sequences_test, maxlen=max_sequence_length, padding='post')
# Build the DNN model
model = Sequential()
model.add(Embedding(input_dim=max_words, output_dim=64, input_length=max_sequence_length))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
# Train the model
model.fit(X_train_padded, y_train, epochs=5, batch_size=32, validation_split=0.2)
# Evaluate the model on the test set
y_pred = (model.predict(X_test_padded) > 0.5).astype("int32")
# Print classification report and accuracy
print("Classification Report:")
print(classification_report(y_test, y_pred))
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("Accuracy:", accuracy_score(y_test, y_pred))
# Save the model
model.save('spam_dnn_model.h5')
# Save the tokenizer
with open('tokenizer_dnn.pkl', 'wb') as tokenizer_file:
tokenizer.word_index = {e: i for e, i in tokenizer.word_index.items() if i <= max_words}
pickle.dump(tokenizer, tokenizer_file)