Upload 4 files

app.py

@@ -0,0 +1,351 @@
+import os 
+import pyaudio
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import time
+import speech_recognition as sr
+from textblob import TextBlob
+import streamlit as st
+import seaborn as sns
+import plotly.express as px
+from datetime import datetime, timedelta
+import gspread
+from google.oauth2.service_account import Credentials
+
+# Set up paths
+csv_file_path = r"C:\Users\Muthuraja\OneDrive\Attachments\Desktop\second\context.csv"  # Path to your CSV file
+output_csv_path = r"C:\Users\Muthuraja\OneDrive\Attachments\Desktop\second\query_results.csv"  # Path to save query results
+
+# Google Sheets setup
+SCOPE = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
+CREDS_PATH = r"C:\Users\Muthuraja\Downloads\modern-cycling-444916-g6-82c207d3eb47.json"  # Provide your Google credentials path
+
+# Initialize Google Sheets connection
+def initialize_google_sheets():
+    credentials = Credentials.from_service_account_file(CREDS_PATH, scopes=SCOPE)
+    try:
+        client = gspread.authorize(credentials)
+        sheet = client.open("SalesStores").sheet1  # Change Google Sheet name to "SalesStores"
+        return sheet
+    except gspread.exceptions.APIError as e:
+        st.error(f"Google Sheets API error: {e}")
+        return None
+
+sheet = initialize_google_sheets()
+
+# Function to safely load the CSV dataset
+def load_csv_safely(file_path):
+    try:
+        # Attempt to read with error handling for bad lines
+        df = pd.read_csv(file_path, on_bad_lines='skip')  # Skips malformed lines
+        # Check if the required columns exist
+        required_columns = ['question', 'product', 'price', 'features', 'ratings', 'discount']
+        for column in required_columns:
+            if column not in df.columns:
+                raise Exception(f"CSV does not contain the required column: '{column}'. Please check your CSV.")
+        
+        # If 'Timestamp' column doesn't exist, create it as NaN or empty
+        if 'Timestamp' not in df.columns:
+            df['Timestamp'] = pd.NaT  # Set it to NaT (Not a Time) initially
+        
+        return df
+    except pd.errors.ParserError as e:
+        st.error(f"Error reading CSV file: {e}")
+        return None
+    except Exception as e:
+        st.error(f"An error occurred: {e}")
+        return None
+
+dataset = load_csv_safely(csv_file_path)  # Load the dataset safely
+embedding_model = SentenceTransformer('all-MiniLM-L6-v2')  # Pre-trained sentence transformer model
+
+# Function to filter data by date
+def filter_data_by_date(data, date_filter):
+    if date_filter == "Today":
+        start_date = datetime.now().replace(hour=0, minute=0, second=0, microsecond=0)
+        data = data[data['Timestamp'] >= start_date]
+    elif date_filter == "One Week":
+        start_date = datetime.now() - timedelta(weeks=1)
+        data = data[data['Timestamp'] >= start_date]
+    return data
+
+# Function to recognize speech using SpeechRecognition and PyAudio in chunks
+def listen_to_speech():
+    recognizer = sr.Recognizer()
+
+    # Initialize PyAudio microphone stream
+    with sr.Microphone() as source:
+        recognizer.adjust_for_ambient_noise(source)
+        st.write("Listening...")  # Optional: Add a message to indicate listening state
+        
+        try:
+            # Listen for the audio input
+            audio = recognizer.listen(source, timeout=5, phrase_time_limit=10)  # Listen for up to 10 seconds
+            st.write("Recognizing...")  # Optional: Add a message for recognition process
+            
+            # Use Google's speech recognition to convert audio to text
+            text = recognizer.recognize_google(audio)
+            st.write(f"Recognized: {text}")
+            return text  # Return the text detected from the audio
+        except sr.UnknownValueError:
+            st.error("Sorry, I could not understand the audio.")  # Handle case when the audio is unclear
+            return None
+        except sr.RequestError:
+            st.error("Could not request results from Google Speech Recognition service.")  # Handle network issues
+            return None
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+            return None
+
+# Function to check if the text is a greeting
+def is_greeting(text):
+    greetings = ["hello", "hi", "hey", "good morning", "good afternoon", "good evening", "hola"]
+    return any(greeting in text.lower() for greeting in greetings)
+
+# Function to respond to greetings
+def respond_to_greeting():
+    st.write("Hi there! How can I assist you today? 😊")
+
+# Function to extract the product name from the query
+def extract_product_name(query):
+    # Ensure that all product names are strings and handle NaN values
+    for product in dataset['product'].fillna('Unknown').astype(str):
+        if product.lower() in query.lower():
+            return product
+    return None
+
+# Function to find the best matching answer using embeddings (Retrieve part of RAG)
+def find_answer(query):
+    if dataset is None:
+        return "Dataset not loaded properly."
+
+    # Compute the embedding of the query
+    query_embedding = embedding_model.encode([query])
+
+    # Compute embeddings for all the dataset questions
+    dataset_embeddings = embedding_model.encode(dataset['question'].tolist())
+
+    # Find the closest match using cosine similarity
+    similarities = cosine_similarity(query_embedding, dataset_embeddings)
+
+    # Get the index of the most similar question
+    closest_idx = np.argmax(similarities)
+
+    # Retrieve the product info associated with the closest question
+    closest_question = dataset.iloc[closest_idx]
+    product_name = closest_question['product']
+    price = closest_question['price']
+    features = closest_question['features']
+    ratings = closest_question['ratings']
+    discount = closest_question['discount']
+
+    # Ensure 'Timestamp' column exists before appending
+    if 'Timestamp' not in closest_question.index:
+        closest_question['Timestamp'] = datetime.now()
+
+    # Append the query and answer to the CSV file
+    new_entry = {
+        'question': query,
+        'product': product_name,
+        'price': price,
+        'features': features,
+        'ratings': ratings,
+        'discount': discount,
+        'Timestamp': datetime.now()
+    }
+    new_entry_df = pd.DataFrame([new_entry])
+
+    # Save the new entry to the CSV file
+    new_entry_df.to_csv(output_csv_path, mode='a', header=not os.path.exists(output_csv_path), index=False)
+
+    # Return specific info based on query
+    if "price" in query.lower():
+        return f"The price of {product_name} is {price}"
+    elif "features" in query.lower():
+        return f"Features of {product_name}: {features}"
+    elif "discount" in query.lower():
+        return f"The discount on {product_name} is {discount}%"
+    else:
+        return f"Product: {product_name}\nPrice: {price}\nFeatures: {features}\nRatings: {ratings}\nDiscount: {discount}%"
+
+# Function for sentiment analysis using TextBlob with emojis
+def analyze_sentiment_with_emoji(text):
+    # Create a TextBlob object
+    blob = TextBlob(text)
+    
+    # Get the sentiment polarity (-1 to 1)
+    sentiment_score = blob.sentiment.polarity
+    
+    # Determine sentiment and corresponding emoji based on the polarity score
+    if sentiment_score > 0:
+        sentiment = "Positive"
+        emoji = "😊"  # Happy emoji for positive sentiment
+    elif sentiment_score < 0:
+        sentiment = "Negative"
+        emoji = "😞"  # Sad emoji for negative sentiment
+    else:
+        sentiment = "Neutral"
+        emoji = "😐"  # Neutral emoji for neutral sentiment
+    
+    return sentiment, sentiment_score, emoji
+
+# Function to provide product recommendations (only product names) based on the query
+def recommend_products(query):
+    if dataset is None:
+        return "Dataset not loaded properly."
+
+    # Ensure all product names are strings and handle missing data
+    dataset['product'] = dataset['product'].fillna('Unknown').astype(str)
+
+    # Compute the embedding of the query
+    query_embedding = embedding_model.encode([query])
+
+    # Compute embeddings for all the dataset product names
+    dataset_embeddings = embedding_model.encode(dataset['product'].tolist())
+
+    # Find the closest match using cosine similarity
+    similarities = cosine_similarity(query_embedding, dataset_embeddings)
+
+    # Get the indices of the top 3 recommendations
+    top_indices = np.argsort(similarities[0])[-3:][::-1]  # Get top 3 recommendations
+
+    # Return at least 3 recommendations
+    recommendations = []
+    for idx in top_indices:
+        product = dataset.iloc[idx]
+        recommendations.append({
+            'product': product['product'],
+            'price': product['price'],
+            'features': product['features'],
+            'ratings': product['ratings'],
+            'discount': product['discount']
+        })  # Append product details
+
+    # If there are less than 3 recommendations, pad with default responses
+    while len(recommendations) < 3:
+        recommendations.append({
+            'product': 'No recommendation available',
+            'price': 'N/A',
+            'features': 'N/A',
+            'ratings': 'N/A',
+            'discount': 'N/A'
+        })
+
+    return recommendations
+
+# Function to handle the entire continuous interaction loop
+def continuous_interaction():
+    st.title("Speech Recognition with Product Queries")
+    if st.button("Start Speech Recognition"):
+        while True:  # Loop for continuous listening
+            user_input = listen_to_speech()
+            if user_input:
+                # Check if the user is greeting
+                if is_greeting(user_input):
+                    respond_to_greeting()
+                    continue  # Skip the rest of the code and just greet
+                # Extract product name if mentioned
+                product_name = extract_product_name(user_input)
+                if product_name:
+                    # If the user asks for a product like "iPhone price", respond with product details
+                    st.write(f"Let me check the details for {product_name}:")
+                    product_details = dataset[dataset['product'].str.lower() == product_name.lower()]
+                    if not product_details.empty:
+                        product_info = product_details.iloc[0]
+                        st.write(f"Product: {product_info['product']}")
+                        st.write(f"Price: {product_info['price']}")
+                        st.write(f"Features: {product_info['features']}")
+                        st.write(f"Ratings: {product_info['ratings']}")
+                        st.write(f"Discount: {product_info['discount']}%")
+                    else:
+                        st.write("Sorry, I couldn't find the product you're asking for.")
+                else:
+                    # If no specific product is mentioned, perform normal question answering
+                    answer = find_answer(user_input)
+                    st.write(f"Answer: {answer}")
+                
+                # Sentiment Analysis with Emoji
+                sentiment, sentiment_score, emoji = analyze_sentiment_with_emoji(user_input)
+                st.write(f"Sentiment: {sentiment} (Score: {sentiment_score}) {emoji}")
+
+                # Product Recommendations based on query
+                st.write("Here are some product recommendations based on your query: ")
+                recommendations = recommend_products(user_input)
+                if recommendations:
+                    for idx, rec in enumerate(recommendations, 1):
+                        st.write(f"**Recommendation {idx}:**")
+                        st.write(f"**Product**: {rec['product']}")
+                        st.write(f"**Price**: {rec['price']}")
+                        st.write(f"**Features**: {rec['features']}")
+                        st.write(f"**Ratings**: {rec['ratings']}")
+                        st.write(f"**Discount**: {rec['discount']}%")
+                        st.write("---")  # Separator between recommendations
+
+                # Handle objections if any
+                st.write("Do you like the recommendation or should I try again?")
+                if listen_to_speech():  # Listen for user feedback
+                    pass
+
+# Dashboard function
+def display_dashboard():
+    # Here you can display your dashboard content
+    st.title("Product Dashboard")
+    st.write("Welcome to the product query dashboard!")
+    
+    # Load query results from CSV
+    query_results_df = pd.read_csv(output_csv_path, on_bad_lines='skip')  # Skip bad lines when loading the CSV
+    
+    # Show a summary table of recent queries
+    st.subheader("Recent Queries Summary")
+    st.write(query_results_df.tail(10))  # Show the last 10 queries
+
+    # Sentiment Analysis - Pie Chart for Positive, Negative, Neutral sentiment distribution
+    sentiment_counts = query_results_df['question'].apply(lambda x: analyze_sentiment_with_emoji(x)[0]).value_counts()
+    st.subheader("Sentiment Analysis Distribution")
+    st.write(sentiment_counts)
+    
+    # Pie chart for sentiment distribution
+    sentiment_fig = px.pie(
+        sentiment_counts, 
+        names=sentiment_counts.index, 
+        values=sentiment_counts.values, 
+        title="Sentiment Distribution of Queries"
+    )
+    st.plotly_chart(sentiment_fig)
+
+    # Line Chart - Sentiment score over time (based on Timestamp)
+    query_results_df['Timestamp'] = pd.to_datetime(query_results_df['Timestamp'], errors='coerce')
+    query_results_df['sentiment_score'] = query_results_df['question'].apply(lambda x: analyze_sentiment_with_emoji(x)[1])
+    
+    sentiment_time_fig = px.line(
+        query_results_df, 
+        x='Timestamp', 
+        y='sentiment_score', 
+        title="Sentiment Score Over Time"
+    )
+    st.plotly_chart(sentiment_time_fig)
+    
+    # Product-based Analysis - Product popularity (based on number of queries)
+    product_counts = query_results_df['product'].value_counts()
+    st.subheader("Product Popularity")
+    st.write(product_counts)
+
+    # Pie chart for product popularity
+    product_popularity_fig = px.pie(
+        product_counts, 
+        names=product_counts.index, 
+        values=product_counts.values, 
+        title="Product Popularity"
+    )
+    st.plotly_chart(product_popularity_fig)
+
+# Main code logic for running the application
+if __name__ == "__main__":
+    choice = st.sidebar.selectbox("Select Mode", ["Dashboard", "Speech Recognition"])
+    
+    if choice == "Dashboard":
+        display_dashboard()  # Display dashboard if selected
+    else:
+        continuous_interaction()  # Speech recognition interaction

context.csv

@@ -0,0 +1,54 @@
+question,product,price,features,ratings,discount,Timestamp,
+What is the price of iPhone 13?,iPhone 13,$799,"6.1-inch display, A15 Bionic chip, 12MP camera",4.7,10%,25-01-2025 10:30,
+What are the features of Samsung Galaxy S22?,Samsung Galaxy S22,$999,"6.1-inch Dynamic AMOLED display, Snapdragon 8 Gen 1, 50MP camera",4.8,15%,25-01-2025 11:15,
+Does iPhone 13 have a discount?,iPhone 13,$799,"6.1-inch display, A15 Bionic chip, 12MP camera",4.7,10%,26-01-2025 09:45,
+Tell me about the Samsung Galaxy Watch 5,Samsung Galaxy Watch 5,$279,"1.4-inch AMOLED display, heart rate monitor, GPS",4.5,20%,26-01-2025 12:00,
+"""Tell me about the smartphone""","""Smartphone X""",$499,"""5G, 128GB storage""",4.5,15,,
+"""What are the best phones?""","""iPhone 13""",999,"""5G, 256GB storage""",4.8,10,,
+"""What are the best laptops?""","""MacBook Pro""",$1999,"""16GB RAM, M1 chip""",4.9,5,,
+What is the best sunscreen for summer?,Sunscreen,15.99,"SPF 50, Waterproof, Long-lasting",4.5,10,,
+Can you recommend a winter jacket?,Winter Jacket,120.5,"Water-resistant, Insulated, Windproof",4.7,15,,
+What are the top beach accessories for summer?,Beach Towel,25.99,"Quick-drying, Lightweight, Soft",4.6,20,,
+What is the best winter boots for cold weather?,Winter Boots,79.99,"Thermal insulation, Waterproof, Non-slip sole",4.8,25,,
+Do you have any summer dresses?,Summer Dress,49.99,"Breathable fabric, Stylish, Various sizes",4.3,10,,
+Which heater is best for winter?,Electric Heater,89.99,"Compact, Energy-efficient, Adjustable settings",4.4,15,,
+Can you suggest a good pair of sunglasses for summer?,Sunglasses,19.99,"UV Protection, Stylish design, Polarized",4.7,5,,
+Do you sell winter gloves?,Winter Gloves,18.5,"Thermal lining, Waterproof, Adjustable fit",4.6,20,,
+What is the best cooler for a summer picnic?,Cooler Box,35.99,"Insulated, Easy to carry, Durable",4.4,10,,
+Can you recommend a heated blanket for winter?,Heated Blanket,59.99,"Multiple heat settings, Soft fabric, Machine washable",4.8,30,,
+What is the best sunscreen for summer?,Sunscreen,15.99,"SPF 50, Waterproof, Long-lasting",4.5,10,,
+Can you recommend a winter jacket?,Winter Jacket,120.5,"Water-resistant, Insulated, Windproof",4.7,15,,
+What are the top beach accessories for summer?,Beach Towel,25.99,"Quick-drying, Lightweight, Soft",4.6,20,,
+What is the best winter boots for cold weather?,Winter Boots,79.99,"Thermal insulation, Waterproof, Non-slip sole",4.8,25,,
+Do you have any summer dresses for girls?,Girls' Summer Dress (Floral),39.99,"Breathable fabric, Stylish, Various sizes",4.3,15,,
+What is the best summer dress for boys?,Boys' Summer T-shirt,19.99,"Comfortable, Soft fabric, Various colors",4.5,10,,Rating
+Which heater is best for winter?,Electric Heater,89.99,"Compact, Energy-efficient, Adjustable settings",4.4,15,,4.6
+Can you suggest a good pair of sunglasses for summer?,Sunglasses,19.99,"UV Protection, Stylish design, Polarized",4.7,5,$800,4.7
+Do you sell winter gloves?,Winter Gloves,18.5,"Thermal lining, Waterproof, Adjustable fit",4.6,20,$150,4.8
+What is the best cooler for a summer picnic?,Cooler Box,35.99,"Insulated, Easy to carry, Durable",4.4,10,Price,Rating
+Can you recommend a heated blanket for winter?,Heated Blanket,59.99,"Multiple heat settings, Soft fabric, Machine washable",4.8,30,$1200,4.9
+Can you recommend a good pair of AirPods?,AirPods Pro,249.99,"Active Noise Cancellation, Wireless, Sweat-resistant",4.8,15,,5
+What is the best sports bike for city commuting?,Sports Bike,499.99,"Lightweight, Fast, Ergonomic design",4.6,20,Laptop,5.1
+Which electric car is best for long trips?,Electric Car (Tesla),39999.99,"Autopilot, Long-range, Fast charging",4.9,10,,
+What is the best electric bike for urban areas?,Electric Bike,799.99,"Powerful motor, Long battery life, Comfortable",4.7,25,,
+Can you recommend a family SUV for winter driving?,Family SUV (Toyota),32000,"All-wheel drive, Spacious, Heated seats",4.5,5,,
+"•	Price: $699.99",,,,,,,
+8. Apple iPad Air (4th Gen),iPhone 13,799,"128GB Storage, A15 Bionic Chip, 5G Support, 12MP Camera",4.8,10,,
+"•	Brand: Apple",Samsung Galaxy S21,749,"128GB Storage, Exynos 2100 Chipset, 5G Support, 64MP Camera",4.7,15,,
+"•	Published Year: 2020",OnePlus 9,699,"128GB Storage, Snapdragon 888 Chipset, 5G Support, 48MP Camera",4.5,12,,
+"•	Key Features: A14 Bionic chip",Google Pixel 6,599,"128GB Storage, Google Tensor Chip, 5G Support, 50MP Camera",4.6,8,,
+"•	Price: $599",Xiaomi Mi 11,599,"128GB Storage, Snapdragon 888, 5G Support, 108MP Camera",4.4,18,,
+9. NVIDIA GeForce RTX 3080 Graphics Card,Samsung Galaxy A52,349,"128GB Storage, Snapdragon 720G Chipset, 5G Support, 64MP Camera",4.2,5,,
+"•	Brand: NVIDIA",Realme 8 Pro,279,"128GB Storage, Snapdragon 720G, 4G Support, 108MP Camera",4.3,10,,
+"•	Published Year: 2020",Motorola Moto G Power,199,"64GB Storage, Snapdragon 662, 4G Support, 48MP Camera",4,20,,
+"•	Key Features: 10GB GDDR6X memory", Ray tracing technology, 4K gaming, Real-time AI-powered graphics,,,,
+"•	Price: $699 (varies by model)",Asus laptop,,,,,,
+10. Sony PlayStation 5 (PS5),,,,,,,
+"•	Brand: Sony",,,,,,,
+"•	Published Year: 2020",,,,,,,
+"•	Key Features: Custom SSD for fast load times", Ray tracing support, 4K gaming at 120Hz, DualSense wireless controller with haptic feedback,,,,
+"•	Price: $499 (Standard Edition)",,,,,,,
+What is the price of iPhone 13?,iPhone 13,$799,"6.1-inch display, A15 Bionic chip, 12MP camera",4.7,10%,25-01-2025 10:30,
+What are the features of Samsung Galaxy S22?,Samsung Galaxy S22,$999,"6.1-inch Dynamic AMOLED display, Snapdragon 8 Gen 1, 50MP camera",4.8,15%,25-01-2025 11:15,
+Does iPhone 13 have a discount?,iPhone 13,$799,"6.1-inch display, A15 Bionic chip, 12MP camera",4.7,10%,26-01-2025 09:45,
+Tell me about the Samsung Galaxy Watch 5,Samsung Galaxy Watch 5,$279,"1.4-inch AMOLED display, heart rate monitor, GPS",4.5,20%,26-01-2025 12:00,

modern-cycling-444916-g6-82c207d3eb47.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "modern-cycling-444916-g6",
+  "private_key_id": "82c207d3eb4740dba64878f4b688878d8896e8a4",
+  "private_key": "-----BEGIN PRIVATE KEY-----\nMIIEvQIBADANBgkqhkiG9w0BAQEFAASCBKcwggSjAgEAAoIBAQCW7JkEdI5swNhs\nu6ojAP0ocVTd5ScpyB7/z+04iVOnzBQYveM54hKgktS1G6vwseQcygmSJaoXr4tr\nAwZzdF6FMH+WcoRlMLerZqH4QZY6PngtPm83xd7l+nvDHRKXOfCYe5UymHRyYWI1\nJssAnZ+VaIx9G81NqvZLC1XgV2SDMbK+Y2g3CS0UC0XnROj1S7qm3Yw09RcQLbLf\nNL9k36qhtMpOchXkjgHbGzAY/JhGDQr68zTgWgMG72sEGmDOeSkyJQ6ifevKPGDT\nF9/zX1IrX9edyujd7l2UuL2Z3eBd4EY3lb+yvGWzzXV0fwhIWZy3abygaKFvy+1L\nMnzugr3PAgMBAAECggEANYHugjDcqdv5Hxutpzlbh7Ied4kdyGdl7iYGoYu2eAAX\ng+oWnFf1aK6F8Su9WtmG2Vob6I+n7TvUfv0UlWxFco0OPwWcwM9z3rXFaOG/5Chv\nrQK8pZZmfzy+Eh/Fjo4BKd5uuABrEH5MNjHpuO8pO+xUGqr3r7iUF2kOajoxrX0u\n0uipD41KFzPXWkno5XZX9nfMZnu4V+iNw0V9ELbqToDUaTznYSneAs14vPGxhI0V\niq7jG08gmcfiqocZcS9bLeDtXkGcfpnxW6oAyCXKtN3mR/PMxHRxIE4K4f5FBeuA\nE+55JJW8fe1qJtOKhYQ6Ee8JQpt1HJNUWG/9f+KYAQKBgQDGTrGUachIcsFNvX5Y\nGCc9amPC1utji9v1uFkw7fXuIoTqb2ZctDxLAOaiASlc54tV78de5GOuCINPc/bf\nOLnbZNxuLehSeK2mzb860d2HlhejiI+ZHkn34nQy3aHcQzNZUvJ0mHEGXXJwl7jy\nv+DOodqSC+N07CyfFu0E2g8ZzwKBgQDC1PRXrugMitXVw5UEOk6Sn7z/OwWVHJZW\n9oqjOx6LcNF2oL9RmRt7gLaBODlRfYa9yIqf9iRo4dCH0er8IiwRdyq7i9q0psxD\nCEXmFFs6/bmFQM5ydowhKDN5I63wxttayqEwKdS4YFmKrsQ9hCqrwDPkaUzdXIl9\nsZiIjY8cAQKBgQCXyZYtBkbyBTwmd/ukDGDEppFTilPD70Jes0s5o3qRWsSn+Lq+\nDIr10eu2ZvM1FFnXXmAZJvGRPRzdDOMSewXvgyUiBGuF7K7mNSfBKu/Inz7awmU/\niyqM3T2ZzYDd6mX8YfwI+MHSYGZ+/fLng6zcHJEDJqxkS33gC5lCFHJoiwKBgG66\nFHvYvayTIuAwHXqfoJQYEJOFebC65H5b84K9UKiy33hp9xFq0IGqLw7VY0365x7o\n4E/01dB9tcPa+4975EuwzCp2Wz+cJC5cf005eHfYRx2CLVJEKXOWo1pPesWCXpwE\n2QLEY06+A2Wb2Y+Uk6O0wkknxzVvJ/y1eBjzSsgBAoGAHSU3yG4Yrp2eQ+yaa9Qj\nGl4UgmQMP3S6UISwhu7M+bPiUl+im4OAfTI1CI6HknkBQ0iUv124aUKSlNhCajUa\nHi8UHIX6WzrFOy6WuDGb1B+bqxyN+QFEmWhDcXPx+hIENIYu770RZx1XJlBAoDx8\nssEmKmJ96Nj5ISqOS1SrPdY=\n-----END PRIVATE KEY-----\n",
+  "client_email": "sales-54@modern-cycling-444916-g6.iam.gserviceaccount.com",
+  "client_id": "116249367824185236800",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/sales-54%40modern-cycling-444916-g6.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

requirements.txt

@@ -0,0 +1,18 @@
+PyPDF2
+streamlit
+transformers
+gspread
+google-auth
+pandas
+matplotlib
+reportlab
+SpeechRecognition
+google-auth-oauthlib
+google-auth-httplib2
+plotly
+torch
+datasets
+vaderSentiment
+seaborn
+
+