Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py  —  BizIntel AI Ultra (CSV, Excel, DB; large‑file safe)
+# app.py  —  BizIntel AI Ultra  (CSV, Excel, DB; Plotly, Gemini 1.5 Pro)
 
 import os
 import tempfile
@@ -17,7 +17,7 @@ from tools.visuals import histogram_tool, scatter_matrix_tool, corr_heatmap_tool
 from db_connector import fetch_data_from_db, list_tables, SUPPORTED_ENGINES
 
 # ──────────────────────────────────────────────────────────────
-# 1.  GEMINI CONFIG
+# 1.  GEMINI 1.5‑PRO
 # ──────────────────────────────────────────────────────────────
 genai.configure(api_key=os.getenv("GEMINI_APIKEY"))
 gemini = genai.GenerativeModel(
@@ -34,7 +34,7 @@ st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
 TEMP_DIR = tempfile.gettempdir()
 
 # ──────────────────────────────────────────────────────────────
-# 3.  DATA SOURCE (CSV, Excel, or DB)
+# 3.  DATA SOURCE  (CSV, Excel, or DB)
 # ──────────────────────────────────────────────────────────────
 source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
 
@@ -46,28 +46,24 @@ if source == "Upload CSV / Excel":
     if up:
         suffix = up.name.split(".")[-1].lower()
         temp_path = os.path.join(TEMP_DIR, up.name)
-
         with open(temp_path, "wb") as f:
             f.write(up.read())
 
-        if suffix in {"csv"}:
+        if suffix == "csv":
             csv_path = temp_path
             file_type = "csv"
-        else:  # Excel → convert to CSV for downstream tools
+        else:  # Excel → convert sheet0 to CSV
             file_type = "excel"
             try:
-                df_iter = pd.read_excel(temp_path, sheet_name=0, chunksize=100000)  # chunk read
+                df_excel = pd.read_excel(temp_path, sheet_name=0)  # loads first sheet
                 csv_path = os.path.splitext(temp_path)[0] + ".csv"
-                with open(csv_path, "w", newline="", encoding="utf-8") as csv_out:
-                    for i, chunk in enumerate(df_iter):
-                        header = i == 0
-                        chunk.to_csv(csv_out, index=False, header=header, mode="a")
+                df_excel.to_csv(csv_path, index=False)
             except Exception as e:
                 st.error(f"Excel parsing failed: {e}")
                 st.stop()
-        st.success(f"{up.name} saved ✅")
+        st.success(f"{up.name} saved ✅")
 
-else:  # SQL DB path
+else:  # SQL DB
     engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
     conn = st.text_input("SQLAlchemy connection string")
     if conn:
@@ -77,7 +73,7 @@ else:  # SQL DB path
             if st.button("Fetch table"):
                 csv_path = fetch_data_from_db(conn, tbl)
                 file_type = "csv"
-                st.success(f"Fetched **{tbl}** as CSV ✅")
+                st.success(f"Fetched **{tbl}** as CSV ✅")
         except Exception as e:
             st.error(f"Connection failed: {e}")
             st.stop()
@@ -85,16 +81,16 @@ else:  # SQL DB path
 if csv_path is None:
     st.stop()
 
-# Offer original download
+# Download working CSV
 with open(csv_path, "rb") as f:
     st.download_button("⬇️ Download working CSV", f, file_name=os.path.basename(csv_path))
 
 # ──────────────────────────────────────────────────────────────
-# 4.  PREVIEW & DATE COLUMN
+# 4.  PREVIEW & DATE COL
 # ──────────────────────────────────────────────────────────────
-preview_df = pd.read_csv(csv_path, nrows=5)
-st.dataframe(preview_df)
-date_col = st.selectbox("Select date/time column for forecasting", preview_df.columns)
+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)
 
 # ──────────────────────────────────────────────────────────────
 # 5.  LOCAL TOOLS
@@ -102,16 +98,14 @@ date_col = st.selectbox("Select date/time column for forecasting", preview_df.co
 with st.spinner("Parsing dataset…"):
     summary_text = parse_csv_tool(csv_path)
 
-# Trend chart
-with st.spinner("Generating sales trend…"):
+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)
 
-# Forecast
-with st.spinner("Forecasting…"):
+with st.spinner("🔮 Forecasting…"):
     forecast_text = forecast_tool(csv_path, date_col=date_col)
     forecast_png = "forecast_plot.png" if os.path.exists("forecast_plot.png") else None
 
@@ -141,18 +135,17 @@ st.download_button("⬇️ Download Strategy (.md)", strategy_md, file_name="st
 # ──────────────────────────────────────────────────────────────
 # 7.  KPI CARDS + EXPANDER
 # ──────────────────────────────────────────────────────────────
-full_df = pd.read_csv(csv_path, nrows=None, low_memory=False)
+full_df = pd.read_csv(csv_path, low_memory=False)
 total_rows = len(full_df)
-num_cols = len(full_df.columns)
+num_cols   = len(full_df.columns)
 missing_pct = full_df.isna().mean().mean() * 100
 
 st.markdown("---")
 st.subheader("📑 Dataset Overview")
-
-k1, k2, k3 = st.columns(3)
-k1.metric("Rows",     f"{total_rows:,}")
-k2.metric("Columns",  str(num_cols))
-k3.metric("Missing %", f"{missing_pct:.1f}%")
+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}%")
 
 with st.expander("🔎 Detailed descriptive statistics"):
     stats_df = full_df.describe().T.reset_index().rename(columns={"index": "Feature"})
@@ -167,16 +160,16 @@ with st.expander("🔎 Detailed descriptive statistics"):
 st.markdown("---")
 st.subheader("🔍 Optional Exploratory Visuals")
 
-numeric_cols = preview_df.select_dtypes("number").columns
+num_cols = df_preview.select_dtypes("number").columns
 
 if st.checkbox("Histogram"):
-    hist_col = st.selectbox("Variable", numeric_cols, key="hist")
-    st.plotly_chart(histogram_tool(csv_path, hist_col), use_container_width=True)
+    hcol = st.selectbox("Variable", num_cols, key="hist")
+    st.plotly_chart(histogram_tool(csv_path, hcol), use_container_width=True)
 
 if st.checkbox("Scatter‑matrix"):
-    sel_cols = st.multiselect("Choose columns", numeric_cols, default=numeric_cols[:3])
-    if sel_cols:
-        st.plotly_chart(scatter_matrix_tool(csv_path, sel_cols), use_container_width=True)
+    sel = st.multiselect("Choose columns", num_cols, default=num_cols[:3])
+    if sel:
+        st.plotly_chart(scatter_matrix_tool(csv_path, sel), use_container_width=True)
 
 if st.checkbox("Correlation heat‑map"):
     st.plotly_chart(corr_heatmap_tool(csv_path), use_container_width=True)