Update app.py

app.py

@@ -23,13 +23,11 @@ st.set_page_config(page_title="Data-Vision Pro", layout="wide", initial_sidebar_
 # Load environment variables
 load_dotenv()
 
-# Initialize Groq client
+# Initialize Groq client and embeddings
 client = Groq(api_key=os.getenv("GROQ_API_KEY"))
-
-# Initialize HuggingFace embeddings
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-# Custom CSS for fullscreen and responsiveness
+# Custom CSS with improved spacing, sizing, and UI/UX
 st.markdown("""
     <style>
     :root {
@@ -37,22 +35,25 @@ st.markdown("""
         --blue: #5C89BC;
         --gold: #A87E01;
         --text-color: #333333;
+        --spacing-unit: 1.5rem;
     }
     .stApp {
         background-color: var(--silver);
         font-family: 'Inter', sans-serif;
-        padding: 1rem;
+        padding: var(--spacing-unit);
         height: 100vh;
-        width: 100vw;
         overflow-y: auto;
+        display: flex;
+        flex-direction: column;
     }
     .header {
         background-color: var(--blue);
         color: white;
-        padding: 1.5rem;
+        padding: var(--spacing-unit);
         border-radius: 8px;
         text-align: center;
-        margin-bottom: 1rem;
+        margin-bottom: var(--spacing-unit);
+        box-shadow: 0 2px 10px rgba(0,0,0,0.1);
     }
     .header-title {
         font-size: 2rem;
@@ -62,26 +63,27 @@ st.markdown("""
     .header-subtitle {
         font-size: 1rem;
         margin-top: 0.5rem;
+        opacity: 0.9;
     }
     .nav-bar {
         background-color: white;
         border-radius: 8px;
         padding: 1rem;
         display: flex;
-        justify-content: space-between;
+        gap: 1rem;
         align-items: center;
         flex-wrap: wrap;
-        gap: 1rem;
-        margin-bottom: 1.5rem;
+        margin-bottom: var(--spacing-unit);
+        box-shadow: 0 2px 5px rgba(0,0,0,0.05);
     }
     .nav-item {
         color: var(--blue);
         font-weight: 500;
-        cursor: pointer;
-        padding: 0.5rem 1rem;
+        padding: 0.75rem 1.5rem;
         border-radius: 5px;
-        flex: 1;
         text-align: center;
+        transition: all 0.2s ease;
+        flex: 1;
     }
     .nav-item:hover {
         background-color: var(--gold);
@@ -90,69 +92,93 @@ st.markdown("""
     .main-container {
         background-color: white;
         border-radius: 8px;
-        padding: 1.5rem;
-        min-height: 60vh;
-        margin-bottom: 1.5rem;
+        padding: var(--spacing-unit);
+        flex-grow: 1;
+        margin-bottom: var(--spacing-unit);
+        box-shadow: 0 2px 5px rgba(0,0,0,0.05);
     }
     .chat-container {
         background-color: white;
-        border-radius: 8px;
-        padding: 1.5rem;
-        margin-bottom: 1rem;
+        border-radius: 8px 8px 0 0;
+        padding: 1rem;
+        position: fixed;
+        bottom: 0;
+        left: var(--spacing-unit);
+        right: var(--spacing-unit);
+        max-height: 40vh;
+        overflow-y: auto;
+        box-shadow: 0 -2px 10px rgba(0,0,0,0.1);
+        z-index: 1000;
+    }
+    .chat-message-container {
+        margin-bottom: 0.5rem;
     }
     .user-message, .bot-message {
-        padding: 1rem;
+        padding: 0.75rem 1rem;
         border-radius: 12px;
         margin-bottom: 0.5rem;
-        max-width: 80%;
+        max-width: 70%;
+        word-wrap: break-word;
     }
     .user-message {
         background-color: var(--blue);
         color: white;
         margin-left: auto;
+        box-shadow: 0 1px 3px rgba(0,0,0,0.1);
     }
     .bot-message {
         background-color: #F0F0F0;
         color: var(--text-color);
         margin-right: auto;
+        box-shadow: 0 1px 3px rgba(0,0,0,0.05);
     }
     .footer {
         text-align: center;
         color: var(--text-color);
         font-size: 0.9rem;
         padding: 1rem 0;
+        margin-top: auto;
     }
     h2 {
         color: var(--blue);
         border-bottom: 2px solid var(--gold);
         padding-bottom: 0.5rem;
         font-size: 1.5rem;
+        margin-bottom: 1rem;
     }
     .stButton > button {
         background-color: var(--gold);
         color: white;
         border-radius: 5px;
-        padding: 0.5rem 1rem;
+        padding: 0.75rem 1.5rem;
+        font-weight: 500;
+        transition: background-color 0.2s ease;
     }
     .stButton > button:hover {
         background-color: #8C6B01;
     }
+    .stTextInput > div > div > input {
+        border-radius: 5px;
+        padding: 0.75rem;
+    }
     @media (max-width: 768px) {
         .header-title { font-size: 1.5rem; }
         .header-subtitle { font-size: 0.9rem; }
-        .nav-bar { flex-direction: column; padding: 0.5rem; }
-        .nav-item { margin: 0.5rem 0; width: 100%; }
-        .main-container, .chat-container { padding: 1rem; }
+        .nav-bar { flex-direction: column; padding: 0.75rem; gap: 0.5rem; }
+        .nav-item { padding: 0.5rem; }
+        .main-container { padding: 1rem; }
+        .chat-container { padding: 0.75rem; max-height: 50vh; }
         h2 { font-size: 1.2rem; }
     }
     @media (max-width: 480px) {
         .header-title { font-size: 1.2rem; }
-        .stApp { padding: 0.5rem; }
+        .stApp { padding: 0.75rem; }
+        .chat-container { left: 0.75rem; right: 0.75rem; }
     }
     </style>
 """, unsafe_allow_html=True)
 
-# Helper Functions (unchanged, included for completeness)
+# Helper Functions (fully implemented from original intent)
 def enhance_section_title(title):
     st.markdown(f"<h2>{title}</h2>", unsafe_allow_html=True)
 
@@ -162,41 +188,126 @@ def update_cleaned_data(df):
         st.session_state.data_versions = [st.session_state.raw_data.copy()]
     st.session_state.data_versions.append(df.copy())
     st.session_state.dataset_text = convert_df_to_text(df)
+    st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
     st.success("✅ Action completed!")
     st.rerun()
 
 def convert_df_to_text(df):
-    # (Existing implementation)
-    pass
+    text = f"Dataset Summary: {df.shape[0]} rows, {df.shape[1]} columns\n"
+    text += f"Missing Values: {df.isna().sum().sum()}\nColumns:\n"
+    for col in df.columns:
+        text += f"- {col} ({df[col].dtype}): "
+        if pd.api.types.is_numeric_dtype(df[col]):
+            text += f"Mean={df[col].mean():.2f}, Min={df[col].min()}, Max={df[col].max()}"
+        else:
+            text += f"Unique={df[col].nunique()}, Top={df[col].mode()[0] if not df[col].mode().empty else 'N/A'}"
+        text += f", Missing={df[col].isna().sum()}\n"
+    return text
 
 def create_vector_store(df_text):
-    # (Existing implementation)
-    pass
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as temp_file:
+        temp_file.write(df_text)
+        temp_path = temp_file.name
+    loader = TextLoader(temp_path)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    texts = text_splitter.split_documents(documents)
+    vector_store = FAISS.from_documents(texts, embeddings)
+    os.unlink(temp_path)
+    return vector_store
 
 def update_vector_store_with_plot(plot_text, existing_vector_store):
-    # (Existing implementation)
-    pass
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    plot_docs = text_splitter.create_documents([plot_text])
+    if existing_vector_store:
+        existing_vector_store.add_documents(plot_docs)
+    else:
+        existing_vector_store = FAISS.from_documents(plot_docs, embeddings)
+    return existing_vector_store
 
 def extract_plot_data(plot_info, df):
-    # (Existing implementation)
-    pass
+    plot_type = plot_info.get("type", "").lower()
+    x_col = plot_info.get("x", "")
+    y_col = plot_info.get("y", "")
+    if x_col not in df.columns or (plot_type == "scatter" and y_col not in df.columns):
+        return None, "Invalid column names."
+    if plot_type == "scatter":
+        fig = px.scatter(df, x=x_col, y=y_col)
+        return fig, f"Scatter plot: {x_col} vs {y_col}"
+    elif plot_type == "histogram":
+        fig = px.histogram(df, x=x_col)
+        return fig, f"Histogram of {x_col}"
+    return None, "Unsupported plot type."
 
 def get_chatbot_response(user_input, app_mode, vector_store=None, model="llama3-70b-8192"):
-    # (Existing implementation)
-    pass
+    context = ""
+    if vector_store:
+        docs = vector_store.similarity_search(user_input, k=3)
+        context = "\n\nData Context:\n" + "\n".join([f"- {doc.page_content}" for doc in docs])
+    system_prompt = f"You are an expert in {app_mode.lower()} analysis.{context}"
+    response = client.chat.completions.create(
+        model=model,
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_input}
+        ],
+        temperature=0.7,
+        max_tokens=1024
+    ).choices[0].message.content
+    return response
+
+# Command Functions (basic implementations from original intent)
+def drop_columns(columns):
+    if 'cleaned_data' in st.session_state:
+        df = st.session_state.cleaned_data.drop(columns=columns)
+        update_cleaned_data(df)
 
-# Command Functions (unchanged)
-def drop_columns(columns): pass
-def generate_scatter_plot(params): pass
-def generate_histogram(params): pass
-def analyze_plot(): pass
-def parse_command(command): pass
+def generate_scatter_plot(params):
+    if 'cleaned_data' in st.session_state:
+        df = st.session_state.cleaned_data
+        x, y = params.get("x"), params.get("y")
+        if x in df.columns and y in df.columns:
+            fig = px.scatter(df, x=x, y=y)
+            st.plotly_chart(fig, use_container_width=True)
+            plot_text = f"Scatter plot of {x} vs {y}"
+            st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
+
+def generate_histogram(params):
+    if 'cleaned_data' in st.session_state:
+        df = st.session_state.cleaned_data
+        x = params.get("x")
+        if x in df.columns:
+            fig = px.histogram(df, x=x)
+            st.plotly_chart(fig, use_container_width=True)
+            plot_text = f"Histogram of {x}"
+            st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
+
+def analyze_plot():
+    if 'cleaned_data' in st.session_state:
+        st.write("Plot analysis not fully implemented yet.")
+
+def parse_command(command):
+    command = command.lower().strip()
+    if "drop" in command:
+        columns = re.findall(r"drop\s+columns?\s+(.+)", command)
+        if columns:
+            cols = [col.strip() for col in columns[0].split(",")]
+            return {"action": "drop_columns", "columns": cols}
+    elif "scatter" in command:
+        match = re.search(r"scatter\s+plot\s+x=(\w+)\s+y=(\w+)", command)
+        if match:
+            return {"action": "scatter_plot", "x": match.group(1), "y": match.group(2)}
+    elif "histogram" in command:
+        match = re.search(r"histogram\s+of\s+(\w+)", command)
+        if match:
+            return {"action": "histogram", "x": match.group(1)}
+    return None
 
 # Dataset Preview
 def display_dataset_preview():
     if 'cleaned_data' in st.session_state:
         st.subheader("Dataset Preview")
-        st.dataframe(st.session_state.cleaned_data.head(), use_container_width=True)
+        st.dataframe(st.session_state.cleaned_data.head(), use_container_width=True, height=200)
 
 # Main App
 def main():
@@ -209,90 +320,119 @@ def main():
     """, unsafe_allow_html=True)
 
     # Navigation Bar
-    st.markdown('<div class="nav-bar">', unsafe_allow_html=True)
-    col1, col2, col3, col4 = st.columns([1, 1, 1, 1])
-    with col1:
-        uploaded_file = st.file_uploader("Upload File", type=["csv", "xlsx"], key="file_uploader")
-    with col2:
-        app_mode = st.selectbox("Mode", ["Data Upload", "Data Cleaning", "EDA"], label_visibility="collapsed")
-    with col3:
-        model = st.selectbox("Model", ["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"], label_visibility="collapsed")
-    with col4:
-        if 'cleaned_data' in st.session_state:
-            csv = st.session_state.cleaned_data.to_csv(index=False)
-            st.download_button(label="Download", data=csv, file_name='cleaned_data.csv', mime='text/csv')
-    st.markdown('</div>', unsafe_allow_html=True)
+    with st.container():
+        st.markdown('<div class="nav-bar">', unsafe_allow_html=True)
+        col1, col2, col3, col4 = st.columns([2, 2, 2, 1])
+        with col1:
+            uploaded_file = st.file_uploader("Upload File", type=["csv", "xlsx"], key="file_uploader")
+        with col2:
+            app_mode = st.selectbox("Mode", ["Data Upload", "Data Cleaning", "EDA"], label_visibility="collapsed")
+        with col3:
+            model = st.selectbox("Model", ["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"], label_visibility="collapsed")
+        with col4:
+            if 'cleaned_data' in st.session_state:
+                csv = st.session_state.cleaned_data.to_csv(index=False)
+                st.download_button(label="Download", data=csv, file_name='cleaned_data.csv', mime='text/csv')
+        st.markdown('</div>', unsafe_allow_html=True)
 
     # Initialize Session State
     if 'vector_store' not in st.session_state:
         st.session_state.vector_store = None
     if 'chat_history' not in st.session_state:
         st.session_state.chat_history = []
+    if 'raw_data' not in st.session_state:
+        st.session_state.raw_data = None
+    if 'cleaned_data' not in st.session_state:
+        st.session_state.cleaned_data = None
+    if 'data_versions' not in st.session_state:
+        st.session_state.data_versions = []
+    if 'dataset_text' not in st.session_state:
+        st.session_state.dataset_text = ""
 
     # Main Content
-    st.markdown('<div class="main-container">', unsafe_allow_html=True)
-    display_dataset_preview()
+    with st.container():
+        st.markdown('<div class="main-container">', unsafe_allow_html=True)
+        display_dataset_preview()
 
-    if app_mode == "Data Upload":
-        enhance_section_title("📤 Data Upload")
-        if uploaded_file:
-            try:
-                df = pd.read_csv(uploaded_file) if uploaded_file.name.endswith('.csv') else pd.read_excel(uploaded_file)
-                st.session_state.raw_data = df
-                st.session_state.cleaned_data = df.copy()
-                st.session_state.dataset_text = convert_df_to_text(df)
-                st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
-                st.session_state.data_versions = [df.copy()]
-                col1, col2, col3 = st.columns(3)
-                with col1: st.metric("Rows", df.shape[0])
-                with col2: st.metric("Columns", df.shape[1])
-                with col3: st.metric("Missing", df.isna().sum().sum())
-                if st.button("Generate Report"):
-                    pr = ProfileReport(df, explorative=True)
-                    st_profile_report(pr)
-            except Exception as e:
-                st.error(f"Error: {e}")
+        if app_mode == "Data Upload":
+            enhance_section_title("📤 Data Upload")
+            if uploaded_file:
+                try:
+                    df = pd.read_csv(uploaded_file) if uploaded_file.name.endswith('.csv') else pd.read_excel(uploaded_file)
+                    st.session_state.raw_data = df
+                    st.session_state.cleaned_data = df.copy()
+                    st.session_state.dataset_text = convert_df_to_text(df)
+                    st.session_state.vector_store = create_vector_store(st.session_state.dataset_text)
+                    st.session_state.data_versions = [df.copy()]
+                    col1, col2, col3 = st.columns(3)
+                    with col1: st.metric("Rows", df.shape[0])
+                    with col2: st.metric("Columns", df.shape[1])
+                    with col3: st.metric("Missing", df.isna().sum().sum())
+                    if st.button("Generate Report"):
+                        pr = ProfileReport(df, explorative=True)
+                        st_profile_report(pr)
+                except Exception as e:
+                    st.error(f"Error: {e}")
 
-    elif app_mode == "Data Cleaning":
-        enhance_section_title("🧹 Data Cleaning")
-        if 'cleaned_data' not in st.session_state:
-            st.warning("Upload data first.")
-            return
-        df = st.session_state.cleaned_data.copy()
-        # Simplified cleaning options (expand as needed)
-        columns_to_drop = st.multiselect("Drop Columns", df.columns)
-        if st.button("Drop Selected"):
-            new_df = df.drop(columns=columns_to_drop)
-            update_cleaned_data(new_df)
+        elif app_mode == "Data Cleaning":
+            enhance_section_title("🧹 Data Cleaning")
+            if 'cleaned_data' not in st.session_state:
+                st.warning("Upload data first.")
+            else:
+                df = st.session_state.cleaned_data.copy()
+                columns_to_drop = st.multiselect("Drop Columns", df.columns)
+                if st.button("Drop Selected"):
+                    new_df = df.drop(columns=columns_to_drop)
+                    update_cleaned_data(new_df)
 
-    elif app_mode == "EDA":
-        enhance_section_title("🔍 EDA")
-        if 'cleaned_data' not in st.session_state:
-            st.warning("Upload data first.")
-            return
-        df = st.session_state.cleaned_data.copy()
-        plot_type = st.selectbox("Plot Type", ["Scatter Plot", "Histogram"])
-        x_axis = st.selectbox("X-axis", df.columns)
-        if plot_type == "Scatter Plot":
-            y_axis = st.selectbox("Y-axis", df.columns)
-            if st.button("Generate"):
-                fig = px.scatter(df, x=x_axis, y=y_axis)
-                st.plotly_chart(fig, use_container_width=True)
+        elif app_mode == "EDA":
+            enhance_section_title("🔍 EDA")
+            if 'cleaned_data' not in st.session_state:
+                st.warning("Upload data first.")
+            else:
+                df = st.session_state.cleaned_data.copy()
+                plot_type = st.selectbox("Plot Type", ["Scatter Plot", "Histogram"])
+                x_axis = st.selectbox("X-axis", df.columns)
+                if plot_type == "Scatter Plot":
+                    y_axis = st.selectbox("Y-axis", df.columns)
+                    if st.button("Generate"):
+                        fig = px.scatter(df, x=x_axis, y=y_axis)
+                        st.plotly_chart(fig, use_container_width=True)
+                        plot_text = f"Scatter plot of {x_axis} vs {y_axis}"
+                        st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
+                else:
+                    if st.button("Generate"):
+                        fig = px.histogram(df, x=x_axis)
+                        st.plotly_chart(fig, use_container_width=True)
+                        plot_text = f"Histogram of {x_axis}"
+                        st.session_state.vector_store = update_vector_store_with_plot(plot_text, st.session_state.vector_store)
 
-    st.markdown('</div>', unsafe_allow_html=True)
+        st.markdown('</div>', unsafe_allow_html=True)
 
     # Chatbot
-    st.markdown('<div class="chat-container">', unsafe_allow_html=True)
-    st.subheader("💬 Chatbot")
-    for message in st.session_state.chat_history:
-        with st.chat_message(message["role"]):
-            st.markdown(f'<div class="{message["role"]}-message">{message["content"]}</div>', unsafe_allow_html=True)
-    if user_input := st.chat_input("Ask anything..."):
-        st.session_state.chat_history.append({"role": "user", "content": user_input})
-        response = get_chatbot_response(user_input, app_mode, st.session_state.vector_store, model)
-        st.session_state.chat_history.append({"role": "assistant", "content": response})
-        st.rerun()
-    st.markdown('</div>', unsafe_allow_html=True)
+    with st.container():
+        st.markdown('<div class="chat-container">', unsafe_allow_html=True)
+        st.subheader("💬 Chatbot")
+        for message in st.session_state.chat_history:
+            with st.container():
+                st.markdown(f'<div class="chat-message-container"><div class="{message["role"]}-message">{message["content"]}</div></div>', unsafe_allow_html=True)
+        if user_input := st.chat_input("Ask anything..."):
+            command = parse_command(user_input)
+            if command:
+                if command["action"] == "drop_columns":
+                    drop_columns(command["columns"])
+                elif command["action"] == "scatter_plot":
+                    generate_scatter_plot({"x": command["x"], "y": command["y"]})
+                elif command["action"] == "histogram":
+                    generate_histogram({"x": command["x"]})
+                st.session_state.chat_history.append({"role": "user", "content": user_input})
+                st.session_state.chat_history.append({"role": "assistant", "content": "Command executed."})
+            else:
+                st.session_state.chat_history.append({"role": "user", "content": user_input})
+                response = get_chatbot_response(user_input, app_mode, st.session_state.vector_store, model)
+                st.session_state.chat_history.append({"role": "assistant", "content": response})
+            st.rerun()
+        st.markdown('</div>', unsafe_allow_html=True)
 
     # Footer
     st.markdown('<div class="footer">Built with Streamlit & Groq</div>', unsafe_allow_html=True)