Update app.py

app.py

@@ -0,0 +1,114 @@
+import numpy as np
+import pandas as pd
+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, LSTM, Dense
+from tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from tensorflow.keras import utils
+import os
+import matplotlib.pyplot as plt
+from nltk.tokenize import word_tokenize
+import nltk
+import gradio as gr
+nltk.download('punkt')
+from wordcloud import WordCloud, STOPWORDS
+
+# Load the dataset
+df = pd.read_csv("Twitter_Data.csv")
+
+# Check for missing values and fill or drop them accordingly
+df['clean_text'].fillna('', inplace=True)
+df.dropna(subset=['category'], inplace=True)
+df.drop_duplicates(inplace=True)
+
+# Tokenize words
+tokenized_text = [word_tokenize(text.lower()) for text in df['clean_text']]
+
+# Word2Vec model
+from gensim.models import Word2Vec
+model = Word2Vec(tokenized_text, vector_size=100, window=5, min_count=1, workers=4)
+
+# Define input and target variables
+X = df['clean_text']
+y = df['category']
+
+# Encode target variable
+encoder = LabelEncoder()
+y = encoder.fit_transform(y)
+y = utils.to_categorical(y)
+
+# Tokenize text
+tokenizer = Tokenizer()
+tokenizer.fit_on_texts(X)
+sequences = tokenizer.texts_to_sequences(X)
+
+# Vocabulary size
+vocab_size = len(tokenizer.word_index) + 1
+
+# Max sequence length
+max_seq_length = max([len(seq) for seq in sequences])
+
+# Pad sequences
+X_pad = pad_sequences(sequences, maxlen=max_seq_length)
+
+# Train-test split
+X_train, X_test, y_train, y_test = train_test_split(X_pad, y, test_size=0.2, random_state=42)
+
+# Define LSTM model
+model = Sequential()
+model.add(Embedding(input_dim=vocab_size, output_dim=100, input_length=max_seq_length))
+model.add(LSTM(units=128, dropout=0.2, recurrent_dropout=0.2))
+model.add(Dense(units=3, activation='softmax'))
+
+# Compile model
+model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+# Define callbacks
+reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, min_lr=0.001)
+early_stop = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)
+
+# Train model
+history = model.fit(X_train, y_train, batch_size=128, epochs=10, validation_split=0.1, callbacks=[reduce_lr, early_stop])
+
+# Save the model
+model_path = 'sentiment_analysis_model.h5'
+model.save(model_path)
+
+# Define a function to classify sentiment
+def classify_sentiment(text):
+    # Preprocess the text (tokenization, padding, etc.)
+    text_sequence = tokenizer.texts_to_sequences([text])
+    padded_sequence = pad_sequences(text_sequence, maxlen=max_seq_length)
+
+    # Make prediction using the trained model
+    prediction = model.predict(padded_sequence)
+
+    # Convert prediction to class label
+    predicted_label = np.argmax(prediction)
+
+    # Map class label to sentiment
+    sentiment_mapping = {0: "Negative", 1: "Neutral", 2: "Positive"}
+    sentiment = sentiment_mapping[predicted_label]
+
+    return sentiment
+
+# Define the Gradio interface
+def gradio_sentiment_analysis(text):
+    sentiment = classify_sentiment(text)
+    return sentiment
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=gradio_sentiment_analysis,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter text here..."),
+    outputs="text",
+    title="Sentiment Analysis",
+    description="Enter a sentence to classify its sentiment as Positive, Neutral, or Negative."
+)
+
+# Launch the Gradio app
+iface.launch()