CSV DATA Added

app.py

@@ -1,16 +1,12 @@
 import streamlit as st
 import os
-import psycopg2 as pgsql
 import pandas as pd
 import plotly.express as px
-from dotenv import load_dotenv
 import google.generativeai as genai
-
-# Load environment variables
-load_dotenv()
+from io import StringIO
 
 # Configure Genai Key
-genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+genai.configure(api_key=os.environ.get("GOOGLE_API_KEY"))
 
 # Function to load Google Gemini Model and provide queries as response
 def get_gemini_response(question, prompt):
@@ -18,78 +14,83 @@ def get_gemini_response(question, prompt):
     response = model.generate_content([prompt[0], question])
     return response.text.strip()
 
-# Function to retrieve query from the database
-def read_sql_query(sql, db_params):
+# Function to load data from CSV
+@st.cache_data
+def load_data():
+    # This is a sample CSV content. In practice, you'd read this from a file.
+    csv_content = """
+id,product_name,category,price,stock_quantity,supplier,last_restock_date
+1,Cotton T-Shirt,Clothing,19.99,100,FashionCo,2024-03-01
+2,Denim Jeans,Clothing,49.99,75,DenimWorld,2024-02-15
+3,Running Shoes,Footwear,79.99,50,SportyFeet,2024-03-10
+4,Leather Wallet,Accessories,29.99,30,LeatherCrafts,2024-01-20
+5,Smartphone Case,Electronics,14.99,200,TechProtect,2024-03-05
+6,Coffee Maker,Appliances,89.99,25,KitchenTech,2024-02-28
+7,Yoga Mat,Sports,24.99,40,YogaEssentials,2024-03-15
+8,Backpack,Bags,39.99,60,TravelGear,2024-02-10
+9,Sunglasses,Accessories,59.99,35,ShadesMaster,2024-03-20
+10,Bluetooth Speaker,Electronics,69.99,45,SoundWave,2024-01-30
+"""
+    df = pd.read_csv(StringIO(csv_content))
+    df['price'] = pd.to_numeric(df['price'], errors='coerce')
+    df['last_restock_date'] = pd.to_datetime(df['last_restock_date'], errors='coerce')
+    return df
+
+# Function to execute pandas query
+def execute_pandas_query(df, query):
     try:
-        conn = pgsql.connect(**db_params)
-        cur = conn.cursor()
-        cur.execute(sql)
-        rows = cur.fetchall()
-        colnames = [desc[0] for desc in cur.description] if cur.description else []
-        conn.commit()
-        cur.close()
-        conn.close()
-        df = pd.DataFrame(rows, columns=colnames)
-        
-        # Convert 'price' column to numeric if it exists
-        if 'price' in df.columns:
-            df['price'] = pd.to_numeric(df['price'], errors='coerce')
-        
-        return df
+        # This is a very simple and unsafe way to execute queries.
+        # In a real application, you'd need to parse the SQL and translate it to pandas operations.
+        result = eval(f"df.{query}")
+        return result
     except Exception as e:
         st.error(f"An error occurred: {e}")
         return pd.DataFrame()
 
-# Define your PostgreSQL connection parameters
-db_params = {
-    'dbname': 'GeminiPro',
-    'user': 'postgres',
-    'password': 'root',
-    'host': 'localhost',
-    'port': 5432
-}
-
 # Define Your Prompt
 prompt = [
     """
-    You are an expert in converting English questions to SQL queries!
-    The SQL database has a table named 'department_store' with the following columns: 
+    You are an expert in converting English questions to pandas DataFrame operations!
+    The DataFrame 'df' has the following columns: 
     id, product_name, category, price, stock_quantity, supplier, last_restock_date.
     
     Examples:
     - How many products do we have in total? 
-      The SQL command will be: SELECT COUNT(*) FROM department_store;
+      The pandas operation will be: len()
     - What are all the products in the Electronics category? 
-      The SQL command will be: SELECT * FROM department_store WHERE category = 'Electronics';
+      The pandas operation will be: query("category == 'Electronics'")
     
-    The SQL code should not include backticks and should not start with the word 'SQL'.
+    The pandas operation should be a valid Python expression that can be applied to a DataFrame 'df'.
     """
 ]
 
 # Streamlit App
-st.set_page_config(page_title="AutomatiX - Department Store Analytics", layout="wide")
+st.set_page_config(page_title="Department Store Analytics", layout="wide")
+
+# Load data
+df = load_data()
 
 # Sidebar for user input
-st.sidebar.title("AutomatiX - Department Store Chat Interface")
+st.sidebar.title("Department Store Query Interface")
 question = st.sidebar.text_area("Enter your question:", key="input")
 submit = st.sidebar.button("Ask Me")
 
 # Main content area
-st.title("AutomatiX - Department Store Dashboard")
+st.title("Department Store Dashboard")
 
 if submit:
-    with st.spinner("Generating and fetching data..."):
-        sql_query = get_gemini_response(question, prompt)
-        # st.code(sql_query, language="sql")
+    with st.spinner("Generating query and fetching data..."):
+        pandas_query = get_gemini_response(question, prompt)
+        st.code(pandas_query, language="python")
         
-        df = read_sql_query(sql_query, db_params)
+        result_df = execute_pandas_query(df, pandas_query)
         
-        if not df.empty:
+        if not result_df.empty:
             st.success("Query executed successfully!")
             
             # Display data in a table
             st.subheader("Data Table")
-            st.dataframe(df)
+            st.dataframe(result_df)
             
             # Create visualizations based on the data
             st.subheader("Data Visualizations")
@@ -97,25 +98,24 @@ if submit:
             col1, col2 = st.columns(2)
             
             with col1:
-                if 'price' in df.columns and df['price'].notna().any():
-                    fig = px.histogram(df, x='price', title='Price Distribution')
+                if 'price' in result_df.columns and result_df['price'].notna().any():
+                    fig = px.histogram(result_df, x='price', title='Price Distribution')
                     st.plotly_chart(fig, use_container_width=True)
                 
-                if 'category' in df.columns:
-                    category_counts = df['category'].value_counts()
+                if 'category' in result_df.columns:
+                    category_counts = result_df['category'].value_counts()
                     fig = px.pie(values=category_counts.values, names=category_counts.index, title='Products by Category')
                     st.plotly_chart(fig, use_container_width=True)
             
             with col2:
-                if 'last_restock_date' in df.columns:
-                    df['last_restock_date'] = pd.to_datetime(df['last_restock_date'], errors='coerce')
-                    df['restock_month'] = df['last_restock_date'].dt.to_period('M')
-                    restock_counts = df['restock_month'].value_counts().sort_index()
+                if 'last_restock_date' in result_df.columns:
+                    result_df['restock_month'] = result_df['last_restock_date'].dt.to_period('M')
+                    restock_counts = result_df['restock_month'].value_counts().sort_index()
                     fig = px.line(x=restock_counts.index.astype(str), y=restock_counts.values, title='Restocking Trend')
                     st.plotly_chart(fig, use_container_width=True)
                 
-                if 'product_name' in df.columns and 'price' in df.columns and df['price'].notna().any():
-                    top_prices = df.sort_values('price', ascending=False).head(10)
+                if 'product_name' in result_df.columns and 'price' in result_df.columns and result_df['price'].notna().any():
+                    top_prices = result_df.sort_values('price', ascending=False).head(10)
                     fig = px.bar(top_prices, x='product_name', y='price', title='Top 10 Most Expensive Products')
                     st.plotly_chart(fig, use_container_width=True)
         else:
@@ -126,9 +126,4 @@ else:
 
 # Footer
 st.sidebar.markdown("---")
-st.sidebar.info("You can ask questions like:\n"
-"1.What are all the products in the Electronics category?\n"
-"2.What is the average price of products in each category?\n"
-"3.Which products have a stock quantity less than 30?\n"
-"4.What are the top 5 most expensive products?")
-st.sidebar.warning("CopyRights@AutomatiX - Powered by Streamlit and Google Gemini")
+st.sidebar.warning("AutomatiX - Department Store Analytics - Powered by Streamlit and Google Gemini")

app_csv.py → app1.py

@@ -1,12 +1,16 @@
 import streamlit as st
 import os
+import psycopg2 as pgsql
 import pandas as pd
 import plotly.express as px
+from dotenv import load_dotenv
 import google.generativeai as genai
-from io import StringIO
+
+# Load environment variables
+load_dotenv()
 
 # Configure Genai Key
-genai.configure(api_key=os.environ.get("GOOGLE_API_KEY"))
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
 # Function to load Google Gemini Model and provide queries as response
 def get_gemini_response(question, prompt):
@@ -14,83 +18,78 @@ def get_gemini_response(question, prompt):
     response = model.generate_content([prompt[0], question])
     return response.text.strip()
 
-# Function to load data from CSV
-@st.cache_data
-def load_data():
-    # This is a sample CSV content. In practice, you'd read this from a file.
-    csv_content = """
-id,product_name,category,price,stock_quantity,supplier,last_restock_date
-1,Cotton T-Shirt,Clothing,19.99,100,FashionCo,2024-03-01
-2,Denim Jeans,Clothing,49.99,75,DenimWorld,2024-02-15
-3,Running Shoes,Footwear,79.99,50,SportyFeet,2024-03-10
-4,Leather Wallet,Accessories,29.99,30,LeatherCrafts,2024-01-20
-5,Smartphone Case,Electronics,14.99,200,TechProtect,2024-03-05
-6,Coffee Maker,Appliances,89.99,25,KitchenTech,2024-02-28
-7,Yoga Mat,Sports,24.99,40,YogaEssentials,2024-03-15
-8,Backpack,Bags,39.99,60,TravelGear,2024-02-10
-9,Sunglasses,Accessories,59.99,35,ShadesMaster,2024-03-20
-10,Bluetooth Speaker,Electronics,69.99,45,SoundWave,2024-01-30
-"""
-    df = pd.read_csv(StringIO(csv_content))
-    df['price'] = pd.to_numeric(df['price'], errors='coerce')
-    df['last_restock_date'] = pd.to_datetime(df['last_restock_date'], errors='coerce')
-    return df
-
-# Function to execute pandas query
-def execute_pandas_query(df, query):
+# Function to retrieve query from the database
+def read_sql_query(sql, db_params):
     try:
-        # This is a very simple and unsafe way to execute queries.
-        # In a real application, you'd need to parse the SQL and translate it to pandas operations.
-        result = eval(f"df.{query}")
-        return result
+        conn = pgsql.connect(**db_params)
+        cur = conn.cursor()
+        cur.execute(sql)
+        rows = cur.fetchall()
+        colnames = [desc[0] for desc in cur.description] if cur.description else []
+        conn.commit()
+        cur.close()
+        conn.close()
+        df = pd.DataFrame(rows, columns=colnames)
+        
+        # Convert 'price' column to numeric if it exists
+        if 'price' in df.columns:
+            df['price'] = pd.to_numeric(df['price'], errors='coerce')
+        
+        return df
     except Exception as e:
         st.error(f"An error occurred: {e}")
         return pd.DataFrame()
 
+# Define your PostgreSQL connection parameters
+db_params = {
+    'dbname': 'GeminiPro',
+    'user': 'postgres',
+    'password': 'root',
+    'host': 'localhost',
+    'port': 5432
+}
+
 # Define Your Prompt
 prompt = [
     """
-    You are an expert in converting English questions to pandas DataFrame operations!
-    The DataFrame 'df' has the following columns: 
+    You are an expert in converting English questions to SQL queries!
+    The SQL database has a table named 'department_store' with the following columns: 
     id, product_name, category, price, stock_quantity, supplier, last_restock_date.
     
     Examples:
     - How many products do we have in total? 
-      The pandas operation will be: len()
+      The SQL command will be: SELECT COUNT(*) FROM department_store;
     - What are all the products in the Electronics category? 
-      The pandas operation will be: query("category == 'Electronics'")
+      The SQL command will be: SELECT * FROM department_store WHERE category = 'Electronics';
     
-    The pandas operation should be a valid Python expression that can be applied to a DataFrame 'df'.
+    The SQL code should not include backticks and should not start with the word 'SQL'.
     """
 ]
 
 # Streamlit App
-st.set_page_config(page_title="Department Store Analytics", layout="wide")
-
-# Load data
-df = load_data()
+st.set_page_config(page_title="AutomatiX - Department Store Analytics", layout="wide")
 
 # Sidebar for user input
-st.sidebar.title("Department Store Query Interface")
+st.sidebar.title("AutomatiX - Department Store Chat Interface")
 question = st.sidebar.text_area("Enter your question:", key="input")
 submit = st.sidebar.button("Ask Me")
 
 # Main content area
-st.title("Department Store Dashboard")
+st.title("AutomatiX - Department Store Dashboard")
 
 if submit:
-    with st.spinner("Generating query and fetching data..."):
-        pandas_query = get_gemini_response(question, prompt)
-        st.code(pandas_query, language="python")
+    with st.spinner("Generating and fetching data..."):
+        sql_query = get_gemini_response(question, prompt)
+        # st.code(sql_query, language="sql")
         
-        result_df = execute_pandas_query(df, pandas_query)
+        df = read_sql_query(sql_query, db_params)
         
-        if not result_df.empty:
+        if not df.empty:
             st.success("Query executed successfully!")
             
             # Display data in a table
             st.subheader("Data Table")
-            st.dataframe(result_df)
+            st.dataframe(df)
             
             # Create visualizations based on the data
             st.subheader("Data Visualizations")
@@ -98,24 +97,25 @@ if submit:
             col1, col2 = st.columns(2)
             
             with col1:
-                if 'price' in result_df.columns and result_df['price'].notna().any():
-                    fig = px.histogram(result_df, x='price', title='Price Distribution')
+                if 'price' in df.columns and df['price'].notna().any():
+                    fig = px.histogram(df, x='price', title='Price Distribution')
                     st.plotly_chart(fig, use_container_width=True)
                 
-                if 'category' in result_df.columns:
-                    category_counts = result_df['category'].value_counts()
+                if 'category' in df.columns:
+                    category_counts = df['category'].value_counts()
                     fig = px.pie(values=category_counts.values, names=category_counts.index, title='Products by Category')
                     st.plotly_chart(fig, use_container_width=True)
             
             with col2:
-                if 'last_restock_date' in result_df.columns:
-                    result_df['restock_month'] = result_df['last_restock_date'].dt.to_period('M')
-                    restock_counts = result_df['restock_month'].value_counts().sort_index()
+                if 'last_restock_date' in df.columns:
+                    df['last_restock_date'] = pd.to_datetime(df['last_restock_date'], errors='coerce')
+                    df['restock_month'] = df['last_restock_date'].dt.to_period('M')
+                    restock_counts = df['restock_month'].value_counts().sort_index()
                     fig = px.line(x=restock_counts.index.astype(str), y=restock_counts.values, title='Restocking Trend')
                     st.plotly_chart(fig, use_container_width=True)
                 
-                if 'product_name' in result_df.columns and 'price' in result_df.columns and result_df['price'].notna().any():
-                    top_prices = result_df.sort_values('price', ascending=False).head(10)
+                if 'product_name' in df.columns and 'price' in df.columns and df['price'].notna().any():
+                    top_prices = df.sort_values('price', ascending=False).head(10)
                     fig = px.bar(top_prices, x='product_name', y='price', title='Top 10 Most Expensive Products')
                     st.plotly_chart(fig, use_container_width=True)
         else:
@@ -126,4 +126,9 @@ else:
 
 # Footer
 st.sidebar.markdown("---")
-st.sidebar.warning("AutomatiX - Department Store Analytics - Powered by Streamlit and Google Gemini")
+st.sidebar.info("You can ask questions like:\n"
+"1.What are all the products in the Electronics category?\n"
+"2.What is the average price of products in each category?\n"
+"3.Which products have a stock quantity less than 30?\n"
+"4.What are the top 5 most expensive products?")
+st.sidebar.warning("CopyRights@AutomatiX - Powered by Streamlit and Google Gemini")