Update app.py

app.py

@@ -1,10 +1,8 @@
-# app.py  —  BizIntel AI Ultra v2
-# Features: CSV upload, SQL DB fetch, interactive Plotly, Gemini 1.5 Pro,
-# optional EDA, download buttons.
+# app.py  —  BizIntel AI Ultra  (Gemini 1.5 Pro, CSV + DB, interactive Plotly, pro summary)
 
 import os
 import tempfile
-from io import StringIO, BytesIO
+from io import StringIO
 
 import pandas as pd
 import streamlit as st
@@ -13,117 +11,100 @@ import plotly.graph_objects as go
 
 from tools.csv_parser import parse_csv_tool
 from tools.plot_generator import plot_sales_tool
-from tools.forecaster import forecast_tool          # returns text & PNG; we’ll also grab df
-from tools.visuals import (
-    histogram_tool,
-    scatter_matrix_tool,
-    corr_heatmap_tool,
-)
+from tools.forecaster import forecast_tool
+from tools.visuals import histogram_tool, scatter_matrix_tool, corr_heatmap_tool
 from db_connector import fetch_data_from_db, list_tables, SUPPORTED_ENGINES
 
 # ──────────────────────────────────────────────────────────────
-# Gemini 1.5‑Pro
+# 1.  GEMINI CONFIG
 # ──────────────────────────────────────────────────────────────
 genai.configure(api_key=os.getenv("GEMINI_APIKEY"))
 gemini = genai.GenerativeModel(
     "gemini-1.5-pro-latest",
-    generation_config={"temperature": 0.7, "top_p": 0.9, "response_mime_type": "text/plain"},
+    generation_config={
+        "temperature": 0.7,
+        "top_p": 0.9,
+        "response_mime_type": "text/plain",
+    },
 )
 
 # ──────────────────────────────────────────────────────────────
-# Streamlit page
+# 2.  PAGE SETUP
 # ──────────────────────────────────────────────────────────────
 st.set_page_config(page_title="BizIntel AI Ultra", layout="wide")
-st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
+st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
 
 TEMP_DIR = tempfile.gettempdir()
 
 # ──────────────────────────────────────────────────────────────
-# 1.  CHOOSE DATA SOURCE
+# 3.  DATA SOURCE (CSV OR DB)
 # ──────────────────────────────────────────────────────────────
-data_source = st.radio("Select data source", ["Upload CSV", "Connect to SQL Database"])
-csv_path: str | None = None
+source = st.radio("Select data source", ["Upload CSV", "Connect to SQL Database"])
+csv_path = None
 
-if data_source == "Upload CSV":
-    csv_file = st.file_uploader("Upload CSV (≤ 200 MB)", type=["csv"])
-    if csv_file:
-        csv_path = os.path.join(TEMP_DIR, csv_file.name)
+if source == "Upload CSV":
+    up = st.file_uploader("Upload CSV (≤ 200 MB)", type=["csv"])
+    if up:
+        csv_path = os.path.join(TEMP_DIR, up.name)
         with open(csv_path, "wb") as f:
-            f.write(csv_file.read())
+            f.write(up.read())
         st.success("CSV saved ✅")
 
-elif data_source == "Connect to SQL Database":
+else:
     engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
-    conn_str = st.text_input("SQLAlchemy connection string")
-    if conn_str:
+    conn = st.text_input("SQLAlchemy connection string")
+    if conn:
         try:
-            tables = list_tables(conn_str)
+            tbls = list_tables(conn)
+            tbl = st.selectbox("Table", tbls)
+            if st.button("Fetch table"):
+                csv_path = fetch_data_from_db(conn, tbl)
+                st.success(f"Fetched **{tbl}** as CSV ✅")
         except Exception as e:
             st.error(f"Connection failed: {e}")
             st.stop()
 
-        table = st.selectbox("Select table", tables)
-        if st.button("Fetch table"):
-            csv_path = fetch_data_from_db(conn_str, table)
-            st.success(f"Fetched ‘{table}’ into CSV ✅")
-
-# Stop if we still don’t have a CSV
 if csv_path is None:
     st.stop()
 
-# Offer original CSV download
+# Download original CSV
 with open(csv_path, "rb") as f:
-    st.download_button("⬇️ Download original CSV", f, file_name=os.path.basename(csv_path))
+    st.download_button("⬇️ Download original CSV", f, file_name=os.path.basename(csv_path))
 
 # ──────────────────────────────────────────────────────────────
-# 2.  PREVIEW + DATE COL
+# 4.  PREVIEW & DATE COLUMN
 # ──────────────────────────────────────────────────────────────
 df_preview = pd.read_csv(csv_path, nrows=5)
 st.dataframe(df_preview)
-
 date_col = st.selectbox("Select date/time column for forecasting", df_preview.columns)
 
 # ──────────────────────────────────────────────────────────────
-# 3.  RUN LOCAL TOOLS
+# 5.  LOCAL TOOLS: SUMMARY, SALES TREND, FORECAST
 # ──────────────────────────────────────────────────────────────
 with st.spinner("Parsing CSV…"):
     summary_text = parse_csv_tool(csv_path)
 
 with st.spinner("Generating sales trend…"):
     sales_fig = plot_sales_tool(csv_path, date_col=date_col)
-
 if isinstance(sales_fig, go.Figure):
     st.plotly_chart(sales_fig, use_container_width=True)
 else:
     st.warning(sales_fig)
 
 with st.spinner("Forecasting…"):
-    forecast_text = forecast_tool(csv_path, date_col=date_col)   # PNG created
-    # Also capture forecast df from statsmodels if you return it (optional)
-    try:
-        forecast_df = pd.read_csv(StringIO(forecast_text))
-    except Exception:
-        forecast_df = None
-
-# Forecast plot preview
-if os.path.exists("forecast_plot.png"):
-    st.image("forecast_plot.png", caption="Sales Forecast", use_column_width=True)
+    forecast_text = forecast_tool(csv_path, date_col=date_col)
+    forecast_png = "forecast_plot.png" if os.path.exists("forecast_plot.png") else None
 
-# Download forecast CSV if df exists
-if forecast_df is not None and not forecast_df.empty:
-    buf = StringIO()
-    forecast_df.to_csv(buf, index=False)
-    st.download_button("⬇️ Download Forecast CSV", buf.getvalue(), file_name="forecast.csv")
+if forecast_png:
+    st.image(forecast_png, caption="Sales Forecast", use_container_width=True)
 
 # ──────────────────────────────────────────────────────────────
-# 4.  GEMINI STRATEGY
+# 6.  GEMINI STRATEGY
 # ──────────────────────────────────────────────────────────────
 prompt = (
     f"You are **BizIntel Strategist AI**.\n\n"
-    "### CSV Summary\n"
-    f"```\n{summary_text}\n```\n\n"
-    "### Forecast Output\n"
-    f"```\n{forecast_text}\n```\n\n"
+    f"### CSV Summary\n```\n{summary_text}\n```\n\n"
+    f"### Forecast Output\n```\n{forecast_text}\n```\n\n"
     "Return **Markdown** with:\n"
     "1. Five key insights\n"
     "2. Three actionable strategies (with expected impact)\n"
@@ -135,33 +116,47 @@ st.subheader("🚀 Strategy Recommendations (Gemini 1.5 Pro)")
 with st.spinner("Generating insights…"):
     strategy_md = gemini.generate_content(prompt).text
 st.markdown(strategy_md)
+st.download_button("⬇️ Download Strategy (.md)", strategy_md, file_name="strategy.md")
+
+# ──────────────────────────────────────────────────────────────
+# 7.  PROFESSIONAL CSV SUMMARY
+# ──────────────────────────────────────────────────────────────
+st.markdown("---")
+st.subheader("📑 CSV Overview")
+
+full_df = pd.read_csv(csv_path)
+total_rows = len(full_df)
+num_cols   = len(full_df.columns)
+missing_pct = full_df.isna().mean().mean() * 100
+
+c1, c2, c3 = st.columns(3)
+c1.metric("Rows",     f"{total_rows:,}")
+c2.metric("Columns",  str(num_cols))
+c3.metric("Missing %", f"{missing_pct:.1f}%")
 
-# Download strategy as Markdown
-st.download_button("⬇️ Download Strategy (.md)", strategy_md, file_name="strategy.md")
+with st.expander("🔎 Detailed descriptive statistics"):
+    stats_df = full_df.describe().T.reset_index().rename(columns={"index": "Feature"})
+    st.dataframe(
+        stats_df.style.format(precision=2).background_gradient(cmap="Blues"),
+        use_container_width=True,
+    )
 
 # ──────────────────────────────────────────────────────────────
-# 5.  OPTIONAL EXPLORATORY VISUALS
+# 8.  OPTIONAL EXPLORATORY VISUALS
 # ──────────────────────────────────────────────────────────────
 st.markdown("---")
 st.subheader("🔍 Optional Exploratory Visuals")
 
-num_cols = df_preview.select_dtypes("number").columns
+num_cols_only = df_preview.select_dtypes("number").columns
 
 if st.checkbox("Histogram"):
-    col = st.selectbox("Variable", num_cols, key="hist")
-    st.plotly_chart(histogram_tool(csv_path, col), use_container_width=True)
+    hcol = st.selectbox("Variable", num_cols_only, key="hist")
+    st.plotly_chart(histogram_tool(csv_path, hcol), use_container_width=True)
 
 if st.checkbox("Scatter‑matrix"):
-    cols = st.multiselect("Choose up to 5 columns", num_cols, default=num_cols[:3])
-    if cols:
-        st.plotly_chart(scatter_matrix_tool(csv_path, cols), use_container_width=True)
+    sm_cols = st.multiselect("Choose up to 5 columns", num_cols_only, default=num_cols_only[:3])
+    if sm_cols:
+        st.plotly_chart(scatter_matrix_tool(csv_path, sm_cols), use_container_width=True)
 
 if st.checkbox("Correlation heat‑map"):
     st.plotly_chart(corr_heatmap_tool(csv_path), use_container_width=True)
-
-# ──────────────────────────────────────────────────────────────
-# 6.  FULL SUMMARY
-# ──────────────────────────────────────────────────────────────
-st.markdown("---")
-st.subheader("📑 CSV Summary (stats)")
-st.text(summary_text)