Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best_model.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,156 @@
+import pickle
+import streamlit as st
+import numpy as np
+import pandas as pd
+import re
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from nltk.corpus import stopwords
+from sklearn.preprocessing import StandardScaler
+import nltk
+
+# Download required NLTK data (for stopwords only)
+nltk.download('stopwords')
+
+# Load the trained model
+model = load_model("/home/petpooja-504/Desktop/lstm/best_model.keras")
+
+# Load the tokenizer
+with open("/home/petpooja-504/Desktop/lstm/tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+# Ensure the tokenizer is valid
+if not hasattr(tokenizer, 'texts_to_sequences'):
+    raise ValueError("Loaded tokenizer is not a valid Keras Tokenizer object.")
+
+# Define constants
+MAX_SEQUENCE_LENGTH = 100
+
+# Simple tokenizer function
+def simple_tokenizer(text):
+    text = text.lower()
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    tokens = text.split()  # Split by whitespace
+    return tokens
+
+# Preprocessing function for input review
+def preprocess_input_review(review_text):
+    tokens = simple_tokenizer(review_text)
+    stop_words = set(stopwords.words('english'))
+    tokens = [word for word in tokens if word not in stop_words]
+    processed_review = ' '.join(tokens)
+    return processed_review
+
+# Convert simplified time strings (e.g., 2H30M or 15M) to minutes
+def time_to_minutes(time_str):
+    if not time_str or pd.isna(time_str):
+        return 0
+    hours, minutes = 0, 0
+    if 'H' in time_str:
+        parts = time_str.split('H')
+        hours = int(parts[0]) if parts[0].isdigit() else 0
+        time_str = parts[1] if len(parts) > 1 else ''
+    if 'M' in time_str and time_str.split('M')[0].isdigit():
+        minutes = int(time_str.split('M')[0])
+    return hours * 60 + minutes
+
+# Prediction function
+def predict_menu_inclusion(food_name, review_text, cook_time, prep_time, total_time, protein, carbs, fat):
+    # Preprocess the review
+    processed_review = preprocess_input_review(review_text)
+    
+    # Tokenize and pad the review
+    review_sequence = tokenizer.texts_to_sequences([processed_review])
+    padded_review = pad_sequences(review_sequence, maxlen=MAX_SEQUENCE_LENGTH)
+    
+    # Prepare numerical features
+    numerical_features = np.array([[time_to_minutes(cook_time), 
+                                     time_to_minutes(prep_time), 
+                                     time_to_minutes(total_time), 
+                                     protein, carbs, fat]])
+    
+    # Normalize numerical features
+    scaler = StandardScaler()
+    numerical_features = scaler.fit_transform(numerical_features)
+    
+    # Predict the rating
+    predicted_rating = model.predict([padded_review, numerical_features]).flatten()[0]
+    
+    # Decide whether to include the item on the menu
+    include_on_menu = predicted_rating > 4  # Threshold for inclusion
+    
+    return {
+        "FoodName": food_name,
+        "PredictedRating": round(predicted_rating, 2),
+        "IncludeOnMenu": include_on_menu
+    }
+
+# Streamlit app with enhanced UI
+st.set_page_config(page_title="Recipe Rating & Menu Optimization", layout="wide")
+
+st.markdown(
+    """
+    <style>
+        .main {
+            background-color: #f5f5f5;
+            font-family: Arial, sans-serif;
+        }
+        h1 {
+            color: #3c3c7b;
+        }
+        .sidebar .sidebar-content {
+            background-color: #eef2f3;
+        }
+        .stButton>button {
+            background-color: #3c3c7b;
+            color: white;
+            border-radius: 5px;
+            font-size: 16px;
+        }
+        .stButton>button:hover {
+            background-color: #2c2c5a;
+        }
+        .prediction-box {
+            background-color: #eaf6f6;
+            padding: 20px;
+            border-radius: 10px;
+            box-shadow: 2px 2px 10px #ccc;
+        }
+        .success {
+            color: green;
+            font-weight: bold;
+        }
+        .error {
+            color: red;
+            font-weight: bold;
+        }
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+
+st.title("🌟 Recipe Rating & Menu Optimization")
+
+st.sidebar.header("📋 Enter Recipe Details")
+food_name = st.sidebar.text_input("🍴 Food Name", value="Paneer Butter Masala")
+review_text = st.sidebar.text_area("📝 Review Text", value="This dish is delicious, rich in flavor, and a favorite among customers!")
+cook_time = st.sidebar.text_input("⏳ Cooking Time (e.g., 15M or 2H30M)", value="30M")
+prep_time = st.sidebar.text_input("🕒 Preparation Time (e.g., 15M or 1H15M)", value="15M")
+total_time = st.sidebar.text_input("📅 Total Time (e.g., 45M or 1H45M)", value="45M")
+protein = st.sidebar.number_input("💪 Protein (grams)", min_value=0.0, step=1.0, value=20.0)
+carbs = st.sidebar.number_input("🍞 Carbohydrates (grams)", min_value=0.0, step=1.0, value=10.0)
+fat = st.sidebar.number_input("🍟 Fat (grams)", min_value=0.0, step=1.0, value=15.0)
+
+if st.sidebar.button("🔮 Predict"):
+    result = predict_menu_inclusion(food_name, review_text, cook_time, prep_time, total_time, protein, carbs, fat)
+    st.markdown("<div class='prediction-box'>", unsafe_allow_html=True)
+    st.subheader("Prediction Results")
+    st.write(f"**🍴 Food Name:** {result['FoodName']}")
+    st.write(f"**⭐ Predicted Rating:** {result['PredictedRating']}")
+    st.write(
+        f"**🍽️ Include on Menu:** "
+        f"<span class='{'success' if result['IncludeOnMenu'] else 'error'}'>"
+        f"{'Yes' if result['IncludeOnMenu'] else 'No'}</span>",
+        unsafe_allow_html=True,
+    )
+    st.markdown("</div>", unsafe_allow_html=True)

best_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df82bb85028058a4aad29289fc19831402212df55c49a49ed16d54ad5ea6b9f0
+size 396137083

requirement.txt

@@ -0,0 +1,6 @@
+streamlit==1.19.0
+tensorflow==2.13.0
+nltk==3.8.1
+scikit-learn==1.2.0
+numpy==1.24.1
+pandas==1.5.3

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d59dc1db30af00e1a5c0a415eeb31b00872f32497b28a57404948c5576fab22
+size 46

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5173d8221d42a1c0de8de69ffda2b8c5573554093225a621dd22991a888d21d8
+size 15690211