Update app.py

app.py

@@ -1,8 +1,7 @@
-# app.py  —  BizIntel AI Ultra  (CSV, Excel, DB; Plotly, Gemini 1.5 Pro)
+# app.py  —  BizIntel AI Ultra (Any metric, CSV/Excel/DB, Plotly, Gemini 1.5 Pro)
 
 import os
 import tempfile
-from io import StringIO
 from typing import Literal
 
 import pandas as pd
@@ -10,14 +9,14 @@ import streamlit as st
 import google.generativeai as genai
 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
-from tools.visuals import histogram_tool, scatter_matrix_tool, corr_heatmap_tool
-from db_connector import fetch_data_from_db, list_tables, SUPPORTED_ENGINES
+from tools.csv_parser      import parse_csv_tool
+from tools.plot_generator  import plot_metric_tool          # NEW generic
+from tools.forecaster      import forecast_metric_tool      # NEW generic
+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
+# 1.  GEMINI CONFIG
 # ──────────────────────────────────────────────────────────────
 genai.configure(api_key=os.getenv("GEMINI_APIKEY"))
 gemini = genai.GenerativeModel(
@@ -26,7 +25,7 @@ gemini = genai.GenerativeModel(
 )
 
 # ──────────────────────────────────────────────────────────────
-# 2.  PAGE SETUP
+# 2.  PAGE CONFIG
 # ──────────────────────────────────────────────────────────────
 st.set_page_config(page_title="BizIntel AI Ultra", layout="wide")
 st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
@@ -36,28 +35,25 @@ TEMP_DIR = tempfile.gettempdir()
 # ──────────────────────────────────────────────────────────────
 # 3.  DATA SOURCE  (CSV, Excel, or DB)
 # ──────────────────────────────────────────────────────────────
-source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
-
+src = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
 csv_path: str | None = None
-file_type: Literal["csv", "excel"] | None = None
+file_kind: Literal["csv", "excel"] | None = None
 
-if source == "Upload CSV / Excel":
+if src == "Upload CSV / Excel":
     up = st.file_uploader("Upload CSV or Excel (≤ 500 MB)", type=["csv", "xlsx", "xls"])
     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 == "csv":
-            csv_path = temp_path
-            file_type = "csv"
-        else:  # Excel → convert sheet0 to CSV
-            file_type = "excel"
+        if up.name.lower().endswith("csv"):
+            csv_path, file_kind = temp_path, "csv"
+        else:  # Excel → convert first sheet to CSV
             try:
-                df_excel = pd.read_excel(temp_path, sheet_name=0)  # loads first sheet
+                df_xl = pd.read_excel(temp_path, sheet_name=0)
                 csv_path = os.path.splitext(temp_path)[0] + ".csv"
-                df_excel.to_csv(csv_path, index=False)
+                df_xl.to_csv(csv_path, index=False)
+                file_kind = "excel"
             except Exception as e:
                 st.error(f"Excel parsing failed: {e}")
                 st.stop()
@@ -65,14 +61,14 @@ if source == "Upload CSV / Excel":
 
 else:  # SQL DB
     engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
-    conn = st.text_input("SQLAlchemy connection string")
+    conn   = st.text_input("SQLAlchemy connection string")
     if conn:
         try:
             tbls = list_tables(conn)
-            tbl = st.selectbox("Table", tbls)
+            tbl  = st.selectbox("Table", tbls)
             if st.button("Fetch table"):
                 csv_path = fetch_data_from_db(conn, tbl)
-                file_type = "csv"
+                file_kind = "csv"
                 st.success(f"Fetched **{tbl}** as CSV ✅")
         except Exception as e:
             st.error(f"Connection failed: {e}")
@@ -81,47 +77,49 @@ else:  # SQL DB
 if csv_path is None:
     st.stop()
 
-# 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 COL
+# 4.  COLUMN PICKERS
 # ──────────────────────────────────────────────────────────────
-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)
+df_head = pd.read_csv(csv_path, nrows=5)
+st.dataframe(df_head)
+
+date_col   = st.selectbox("Select date/time column", df_head.columns)
+numeric_cols = df_head.select_dtypes("number").columns
+metric_col = st.selectbox("Select numeric metric column", numeric_cols)
 
 # ──────────────────────────────────────────────────────────────
-# 5.  LOCAL TOOLS
+# 5.  LOCAL TOOLS (TREND + FORECAST)
 # ──────────────────────────────────────────────────────────────
 with st.spinner("Parsing dataset…"):
     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)
+with st.spinner("📈 Building trend chart…"):
+    trend_fig = plot_metric_tool(csv_path, date_col, metric_col)
+if isinstance(trend_fig, go.Figure):
+    st.plotly_chart(trend_fig, use_container_width=True)
 else:
-    st.warning(sales_fig)
+    st.warning(trend_fig)
 
 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
+    forecast_text = forecast_metric_tool(csv_path, date_col, metric_col)
+    forecast_png  = "forecast_plot.png" if os.path.exists("forecast_plot.png") else None
 
 if forecast_png:
-    st.image(forecast_png, caption="Sales Forecast", use_column_width=True)
+    st.image(forecast_png, caption=f"{metric_col} Forecast", use_column_width=True)
 
 # ──────────────────────────────────────────────────────────────
-# 6.  GEMINI STRATEGY
+# 6.  GEMINI INSIGHTS
 # ──────────────────────────────────────────────────────────────
 prompt = (
     f"You are **BizIntel Strategist AI**.\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\n"
+    f"### Dataset Summary\n```\n{summary_text}\n```\n\n"
+    f"### {metric_col} Forecast\n```\n{forecast_text}\n```\n\n"
+    "Deliver **Markdown** with:\n"
+    f"1. Five key insights focused on **{metric_col}**\n"
+    "2. Three actionable strategies (impact‑oriented)\n"
     "3. Risk factors or anomalies\n"
     "4. Suggested additional visuals\n"
 )
@@ -133,9 +131,9 @@ st.markdown(strategy_md)
 st.download_button("⬇️ Download Strategy (.md)", strategy_md, file_name="strategy.md")
 
 # ──────────────────────────────────────────────────────────────
-# 7.  KPI CARDS + EXPANDER
+# 7.  KPI CARDS + STAT EXPANDER
 # ──────────────────────────────────────────────────────────────
-full_df = pd.read_csv(csv_path, low_memory=False)
+full_df    = pd.read_csv(csv_path, low_memory=False)
 total_rows = len(full_df)
 num_cols   = len(full_df.columns)
 missing_pct = full_df.isna().mean().mean() * 100
@@ -143,8 +141,8 @@ missing_pct = full_df.isna().mean().mean() * 100
 st.markdown("---")
 st.subheader("📑 Dataset Overview")
 c1, c2, c3 = st.columns(3)
-c1.metric("Rows",     f"{total_rows:,}")
-c2.metric("Columns",  str(num_cols))
+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"):
@@ -160,14 +158,12 @@ with st.expander("🔎 Detailed descriptive statistics"):
 st.markdown("---")
 st.subheader("🔍 Optional Exploratory Visuals")
 
-num_cols = df_preview.select_dtypes("number").columns
-
 if st.checkbox("Histogram"):
-    hcol = st.selectbox("Variable", num_cols, key="hist")
-    st.plotly_chart(histogram_tool(csv_path, hcol), use_container_width=True)
+    hist_col = st.selectbox("Variable", numeric_cols, key="hist")
+    st.plotly_chart(histogram_tool(csv_path, hist_col), use_container_width=True)
 
 if st.checkbox("Scatter‑matrix"):
-    sel = st.multiselect("Choose columns", num_cols, default=num_cols[:3])
+    sel = st.multiselect("Choose columns", numeric_cols, default=numeric_cols[:3])
     if sel:
         st.plotly_chart(scatter_matrix_tool(csv_path, sel), use_container_width=True)