Create app.py

app.py

@@ -0,0 +1,83 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from keras.models import load_model
+from huggingface_hub import hf_hub_download
+from keras.preprocessing.text import Tokenizer
+from keras.preprocessing.sequence import pad_sequences
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+from nltk.sentiment.vader import SentimentIntensityAnalyzer
+import nltk
+
+# Download VADER lexicon for sentiment analysis
+nltk.download('vader_lexicon')
+
+# Load the model from Hugging Face
+model_path = hf_hub_download(repo_id="your-username/your-model-repo", filename="my_model.h5")
+model = load_model(model_path)
+
+# Initialize Tokenizer and LabelEncoders
+tokenizer = Tokenizer(num_words=10000, oov_token='<OOV>')
+label_encoders = {
+    'impact': LabelEncoder(),
+    'priority': LabelEncoder(),
+    'category': LabelEncoder(),
+    'urgency': LabelEncoder()
+}
+
+# Function to preprocess input data
+def preprocess_input(short_description, impact, priority, category, urgency):
+    # Encode categorical features
+    input_data = pd.DataFrame({
+        'short_description': [short_description],
+        'impact': [impact],
+        'priority': [priority],
+        'category': [category],
+        'urgency': [urgency]
+    })
+    
+    for column in ['impact', 'priority', 'category', 'urgency']:
+        input_data[column] = label_encoders[column].fit_transform(input_data[column])
+    
+    # Tokenize text data
+    sequences = tokenizer.texts_to_sequences(input_data['short_description'])
+    padded_sequences = pad_sequences(sequences, maxlen=50, padding='post', truncating='post')
+    
+    # Feature engineering: Add sentiment score
+    sid = SentimentIntensityAnalyzer()
+    input_data['sentiment_score'] = input_data['short_description'].apply(lambda x: sid.polarity_scores(x)['compound'])
+    
+    # Normalize numerical features
+    numerical_features = input_data[['impact', 'priority', 'category', 'urgency', 'sentiment_score']]
+    scaler = StandardScaler()
+    scaled_numerical_features = scaler.fit_transform(numerical_features)
+    
+    # Prepare the final input features
+    X_input = np.concatenate([padded_sequences, scaled_numerical_features], axis=1)
+    return X_input, input_data['sentiment_score'].iloc[0]
+
+# Function to make predictions
+def predict(short_description, impact, priority, category, urgency):
+    X_input, sentiment_score = preprocess_input(short_description, impact, priority, category, urgency)
+    predictions = model.predict(X_input)
+    predicted_label = np.argmax(predictions, axis=1)[0]
+    return predicted_label, sentiment_score
+
+# Define Gradio interface
+inputs = [
+    gr.inputs.Textbox(lines=2, placeholder="Enter short description...", label="Short Description"),
+    gr.inputs.Textbox(lines=1, placeholder="Enter impact...", label="Impact (e.g., '2 - Medium')"),
+    gr.inputs.Textbox(lines=1, placeholder="Enter priority...", label="Priority (e.g., '2 - Medium')"),
+    gr.inputs.Textbox(lines=1, placeholder="Enter category...", label="Category (e.g., 'Network')"),
+    gr.inputs.Textbox(lines=1, placeholder="Enter urgency...", label="Urgency (e.g., '1 - High')")
+]
+
+outputs = [
+    gr.outputs.Textbox(label="Predicted Duration Bin"),
+    gr.outputs.Textbox(label="Sentiment Score")
+]
+
+interface = gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title="Issue Resolution Predictor", description="Predict the duration bin and sentiment score based on issue description and related features.")
+
+# Launch the interface
+interface.launch()