Update app.py

app.py

@@ -1,6 +1,6 @@
 # app.py  —  BizIntel AI Ultra  
-# Supports: CSV/Excel/DB ingestion, any numeric metric + date, interactive Plotly, Gemini 1.5 Pro,
-# KPI cards, optional EDA, safe image writes, and updated use_container_width flag.
+# Supports: CSV/Excel/DB ingestion, date+metric plotting, ARIMA forecasting,
+# safe Plotly writes, Gemini 1.5 Pro strategy, KPI cards, optional EDA.
 
 import os
 import tempfile
@@ -12,29 +12,29 @@ import google.generativeai as genai
 import plotly.graph_objects as go
 
 # ──────────────────────────────────────────────────────────────
-# REDIRECT ALL write_image CALLS TO A WRITABLE TEMP DIRECTORY
+# 0) Redirect all Plotly write_image() into a writable temp dir
 # ──────────────────────────────────────────────────────────────
-_tmp = tempfile.gettempdir()
+TMP = tempfile.gettempdir()
 _original_write = go.Figure.write_image
 
 def _safe_write(self, path, *args, **kwargs):
-    fname = os.path.basename(path)
-    safe_path = os.path.join(_tmp, fname)
+    filename = os.path.basename(path)
+    safe_path = os.path.join(TMP, filename)
     return _original_write(self, safe_path, *args, **kwargs)
 
 go.Figure.write_image = _safe_write
 
 # ──────────────────────────────────────────────────────────────
-# TOOL IMPORTS (updated generic versions)
+# 1) Imports for tools & DB connector
 # ──────────────────────────────────────────────────────────────
 from tools.csv_parser      import parse_csv_tool
-from tools.plot_generator  import plot_metric_tool      # date_col, metric_col
-from tools.forecaster      import forecast_metric_tool  # date_col, metric_col
+from tools.plot_generator  import plot_metric_tool      # (csv_path, date_col, metric_col) → Figure or error
+from tools.forecaster      import forecast_metric_tool  # (csv_path, date_col, metric_col) → text + /tmp/forecast_plot.png
 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 1.5-PRO INITIALIZATION
+# 2) Gemini 1.5 Pro initialization
 # ──────────────────────────────────────────────────────────────
 genai.configure(api_key=os.getenv("GEMINI_APIKEY"))
 gemini = genai.GenerativeModel(
@@ -47,71 +47,70 @@ gemini = genai.GenerativeModel(
 )
 
 # ──────────────────────────────────────────────────────────────
-# 2.  STREAMLIT PAGE CONFIG
+# 3) Streamlit page setup
 # ──────────────────────────────────────────────────────────────
 st.set_page_config(page_title="BizIntel AI Ultra", layout="wide")
 st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
-
 TEMP_DIR = tempfile.gettempdir()
 
 # ──────────────────────────────────────────────────────────────
-# 3.  DATA SOURCE: CSV / EXCEL / SQL DATABASE
+# 4) Data source selection: CSV/Excel or SQL Database
 # ──────────────────────────────────────────────────────────────
 source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
-csv_path: str | None = None
+csv_path = None
 
 if source == "Upload CSV / Excel":
-    upload = st.file_uploader("Upload CSV or Excel (≤ 500 MB)", type=["csv", "xlsx", "xls"])
+    upload = st.file_uploader("Upload CSV or Excel (≤ 500 MB)", type=["csv","xlsx","xls"])
     if upload:
-        temp_path = os.path.join(TEMP_DIR, upload.name)
-        with open(temp_path, "wb") as f:
+        tmp_file = os.path.join(TEMP_DIR, upload.name)
+        with open(tmp_file, "wb") as f:
             f.write(upload.read())
 
         if upload.name.lower().endswith(".csv"):
-            csv_path = temp_path
+            csv_path = tmp_file
         else:
             try:
-                df_xl = pd.read_excel(temp_path, sheet_name=0)
-                csv_path = os.path.splitext(temp_path)[0] + ".csv"
+                df_xl = pd.read_excel(tmp_file, sheet_name=0)
+                csv_path = os.path.splitext(tmp_file)[0] + ".csv"
                 df_xl.to_csv(csv_path, index=False)
             except Exception as e:
                 st.error(f"Excel parsing failed: {e}")
                 st.stop()
         st.success(f"{upload.name} saved ✅")
 
-else:  # SQL Database path
+else:
     engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
     conn   = st.text_input("SQLAlchemy connection string")
     if conn:
         try:
             tables = list_tables(conn)
-            table  = st.selectbox("Table", tables)
+            tbl    = st.selectbox("Table", tables)
             if st.button("Fetch table"):
-                csv_path = fetch_data_from_db(conn, table)
-                st.success(f"Fetched **{table}** as CSV ✅")
+                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()
 
-if csv_path is None:
+if not csv_path:
     st.stop()
 
-# Offer download of the working CSV
+# Download the working CSV
 with open(csv_path, "rb") as f:
     st.download_button("⬇️ Download working CSV", f, file_name=os.path.basename(csv_path))
 
 # ──────────────────────────────────────────────────────────────
-# 4.  COLUMN SELECTION: DATE + METRIC
+# 5) Show first rows & let user pick date + numeric metric
 # ──────────────────────────────────────────────────────────────
 df_head = pd.read_csv(csv_path, nrows=5)
 st.dataframe(df_head)
 
-date_col    = st.selectbox("Select date/time column", df_head.columns)
+date_col     = st.selectbox("Select date/time column", df_head.columns)
 numeric_cols = df_head.select_dtypes("number").columns.tolist()
-metric_col  = st.selectbox("Select numeric metric column", numeric_cols)
+metric_col   = st.selectbox("Select numeric metric column", numeric_cols)
 
 # ──────────────────────────────────────────────────────────────
-# 5.  LOCAL ANALYTICS: SUMMARY, TREND, FORECAST
+# 6) Local analysis: summary, trend chart, forecast
 # ──────────────────────────────────────────────────────────────
 with st.spinner("Parsing dataset…"):
     summary_text = parse_csv_tool(csv_path)
@@ -119,14 +118,14 @@ with st.spinner("Parsing dataset…"):
 with st.spinner("Generating trend chart…"):
     trend_fig = plot_metric_tool(csv_path, date_col, metric_col)
 if isinstance(trend_fig, go.Figure):
+    st.subheader("📈 Trend")
     st.plotly_chart(trend_fig, use_container_width=True)
 else:
     st.warning(trend_fig)
 
-with st.spinner("Forecasting…"):
+with st.spinner("Running forecast…"):
     forecast_text = forecast_metric_tool(csv_path, date_col, metric_col)
 
-# Display the forecast image saved under /tmp
 st.subheader(f"🔮 {metric_col} Forecast")
 forecast_png = os.path.join(TEMP_DIR, "forecast_plot.png")
 if os.path.exists(forecast_png):
@@ -135,7 +134,7 @@ else:
     st.warning("Forecast image not found.")
 
 # ──────────────────────────────────────────────────────────────
-# 6.  GEMINI STRATEGY RECOMMENDATIONS
+# 7) Gemini-driven strategy recommendations
 # ──────────────────────────────────────────────────────────────
 prompt = (
     f"You are **BizIntel Strategist AI**.\n\n"
@@ -155,36 +154,34 @@ st.markdown(strategy_md)
 st.download_button("⬇️ Download Strategy (.md)", strategy_md, file_name="strategy.md")
 
 # ──────────────────────────────────────────────────────────────
-# 7.  KPI CARDS + DETAILED STATS EXPANDER
+# 8) KPI cards + detailed Stats
 # ──────────────────────────────────────────────────────────────
 full_df    = pd.read_csv(csv_path, low_memory=False)
 total_rows = len(full_df)
-num_cols   = len(full_df.columns)
+num_cols   = full_df.shape[1]
 missing_pct = full_df.isna().mean().mean() * 100
 
 st.markdown("---")
 st.subheader("📑 Dataset Overview")
-col1, col2, col3 = st.columns(3)
-col1.metric("Rows",     f"{total_rows:,}")
-col2.metric("Columns",  str(num_cols))
-col3.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"})
-    st.dataframe(
-        stats_df.style.format(precision=2).background_gradient(cmap="Blues"),
-        use_container_width=True,
-    )
+    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)
 
 # ──────────────────────────────────────────────────────────────
-# 8.  OPTIONAL EXPLORATORY VISUALS
+# 9) Optional Exploratory Visuals
 # ──────────────────────────────────────────────────────────────
 st.markdown("---")
 st.subheader("🔍 Optional Exploratory Visuals")
 
 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", numeric_cols, key="hist")
+    st.plotly_chart(histogram_tool(csv_path, hcol), use_container_width=True)
 
 if st.checkbox("Scatter-matrix"):
     sel = st.multiselect("Choose columns", numeric_cols, default=numeric_cols[:3])