Update app.py

app.py

@@ -1,152 +1,189 @@
-"""app.py — BizIntel AI Ultra (Gemini‑only, v4)
-Robust BI copilot featuring:
-• CSV / Excel / Parquet uploads + live SQL ingestion
-• Memory‑safe sampling for large files (≤ 5 M rows sample)
-• Gemini‑generated narrative insights & quick schema audit
-• Interactive EDA (histogram + box, correlation heatmap)
-• Tunable ARIMA forecasting (p,d,q & horizon)
-• One‑click strategy brief download
-"""
-from __future__ import annotations
-import io, os, tempfile
-from pathlib import Path
-from typing import List
-
-import pandas as pd
-import plotly.express as px
 import streamlit as st
+import pandas as pd
+import numpy as np
+import tempfile
+from io import BytesIO
 from sqlalchemy import create_engine
+import plotly.express as px
+import matplotlib.pyplot as plt
 from statsmodels.tsa.arima.model import ARIMA
-import google.generativeai as genai
 
-# ───────────────────── 0 · PAGE CONFIG ──────────────────────
+# ── Helpers to read CSV/Excel robustly ───────────────────────────────────────────
+@st.cache_data
+def load_file(uploaded):
+    """Read a CSV or Excel file into a DataFrame."""
+    try:
+        if uploaded.name.lower().endswith((".xls", ".xlsx")):
+            return pd.read_excel(uploaded, engine="openpyxl")
+        else:
+            return pd.read_csv(uploaded)
+    except Exception as e:
+        raise st.Error(f"Error parsing file: {e}")
+
+# ── Helpers for SQL database ────────────────────────────────────────────────────
+SUPPORTED_ENGINES = ["postgresql", "mysql", "mssql+pyodbc", "oracle+cx_oracle"]
+@st.cache_data
+def list_tables(connection_string):
+    engine = create_engine(connection_string)
+    return engine.table_names()
+
+@st.cache_data
+def fetch_table(connection_string, table_name):
+    engine = create_engine(connection_string)
+    return pd.read_sql_table(table_name, engine)
+
+# ── Streamlit page setup ────────────────────────────────────────────────────────
 st.set_page_config(
-    page_title="BizIntel AI Ultra",
-    page_icon="📊",
+    page_title="BizIntel AI Ultra",
     layout="wide",
     initial_sidebar_state="expanded",
 )
+st.title("📊 BizIntel AI Ultra – Advanced Analytics + Gemini 1.5 Pro")
 
-auth_key = None
-try:
-    auth_key = st.secrets["GEMINI_APIKEY"]  # type: ignore[attr-defined]
-except Exception:
-    auth_key = os.getenv("GEMINI_APIKEY")
+# ── Data source selection ───────────────────────────────────────────────────────
+data_source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
 
-if not auth_key:
-    st.error(
-        "❌ **GEMINI_APIKEY** missing. Add it in *Settings → Secrets* or set env var before running."
+df = None
+if data_source == "Upload CSV / Excel":
+    uploaded = st.file_uploader(
+        "Drag & drop file here (≤ 500 MB)",
+        type=["csv", "xls", "xlsx"],
+        accept_multiple_files=False,
     )
-    st.stop()
-
-genai.configure(api_key=auth_key)
-GEM_MODEL = "gemini-1.5-pro-latest"
-TMP = Path(tempfile.gettempdir())
-
-# ───────────────────── 1 · HELPERS ──────────────────────────
-@st.cache_data(show_spinner=False)
-def load_file(buf: io.BufferedReader, sample: bool = False) -> pd.DataFrame:
-    suf = Path(buf.name).suffix.lower()
-    if suf in {".xls", ".xlsx"}:
-        return pd.read_excel(buf, engine="openpyxl")
-    if suf == ".parquet":
-        return pd.read_parquet(buf)
-    return pd.read_csv(buf, nrows=5_000_000 if sample else None)
-
-@st.cache_data(show_spinner=False)
-def list_sql_tables(uri: str) -> List[str]:
-    return create_engine(uri).table_names()
-
-@st.cache_data(show_spinner=True)
-def fetch_sql_table(uri: str, tbl: str) -> pd.DataFrame:
-    return pd.read_sql_table(tbl, create_engine(uri))
-
-@st.cache_data(show_spinner=False)
-def gemini(prompt: str) -> str:
-    return genai.GenerativeModel(GEM_MODEL).generate_content(prompt).text.strip()
-
-# ───────────────────── 2 · DATA LOAD UI ─────────────────────
-st.title("📊 BizIntel AI Ultra — Gemini 1.5 Pro BI Copilot")
-mode = st.sidebar.radio("Data source", ["Upload file", "SQL DB"], horizontal=True)
-
-df: pd.DataFrame = pd.DataFrame()
-if mode == "Upload file":
-    upl = st.sidebar.file_uploader("CSV / Excel / Parquet", ["csv", "xls", "xlsx", "parquet"], help="≤ 2 GB")
-    sample = st.sidebar.checkbox("Sample first 5 M rows only")
-    if upl:
-        df = load_file(upl, sample)
-else:
-    uri = st.sidebar.text_input("SQLAlchemy URI")
-    if uri:
-        tbl = st.sidebar.selectbox("Table", list_sql_tables(uri))
-        if tbl:
-            df = fetch_sql_table(uri, tbl)
-
-if df.empty:
-    st.info("⬅️ Load data to start analysis.")
-    st.stop()
-
-st.success("✅ Data loaded")
-st.dataframe(df.head(), use_container_width=True)
-
-# ───────────────────── 3 · OVERVIEW & GEMINI INSIGHT ─────────
-rows, cols = df.shape
-missing_pct = df.isna().sum().sum() / (rows * cols) * 100
-m1,m2,m3 = st.columns(3)
-m1.metric("Rows", f"{rows:,}")
-m2.metric("Columns", cols)
-m3.metric("Missing %", f"{missing_pct:.1f}")
-
-st.subheader("🧠 Gemini Insights")
-with st.spinner("Generating narrative…"):
-    summ_json = df.describe(include="all", datetime_is_numeric=True).round(2).to_json()
-    st.markdown(gemini(
-        "You are a senior BI analyst. Provide five bullet insights and three actions for this dataset:\n\n" + summ_json
-    ))
-
-# ───────────────────── 4 · TIME‑SERIES PREP ──────────────────
-# attempt datetime coercion
-for col in df.columns:
-    if not pd.api.types.is_datetime64_any_dtype(df[col]):
+    if uploaded:
+        with st.spinner("Loading file…"):
+            df = load_file(uploaded)
+        st.success("✅ File loaded into memory")
+elif data_source == "Connect to SQL Database":
+    engine = st.selectbox("Select DB engine", SUPPORTED_ENGINES)
+    conn_str = st.text_input("Connection string (SQLAlchemy format)", placeholder="e.g. postgresql://user:pass@host:port/dbname")
+    if conn_str:
+        tables = list_tables(conn_str)
+        table = st.selectbox("Choose table", tables)
+        if table:
+            with st.spinner(f"Fetching `{table}`…"):
+                df = fetch_table(conn_str, table)
+            st.success(f"✅ `{table}` loaded from database")
+
+# ── If DataFrame is ready, show overview and proceed ───────────────────────────
+if df is not None:
+    st.markdown("### 🗂️ Preview")
+    st.dataframe(df.head(5), use_container_width=True)
+
+    # Dataset overview metrics
+    n_rows, n_cols = df.shape
+    missing_pct = (df.isna().sum().sum() / (n_rows * n_cols)) * 100
+    st.markdown("---")
+    c1, c2, c3 = st.columns(3)
+    c1.metric("Rows", f"{n_rows:,}")
+    c2.metric("Columns", f"{n_cols:,}")
+    c3.metric("Missing %", f"{missing_pct:.1f}%")
+
+    # Detailed stats
+    st.markdown("#### 📋 Detailed descriptive statistics")
+    st.dataframe(df.describe(include="all").transpose(), use_container_width=True)
+
+    # Optional exploratory visuals
+    st.markdown("---")
+    st.markdown("#### 🔎 Optional Exploratory Visuals")
+    col1, col2, col3 = st.columns(3)
+    with col1:
+        if st.checkbox("Histogram"):
+            num_cols = df.select_dtypes(include="number").columns.tolist()
+            col = st.selectbox("Choose numeric column for histogram", num_cols, key="hist")
+            fig = px.histogram(df, x=col, nbins=30, title=f"Histogram of {col}")
+            st.plotly_chart(fig, use_container_width=True)
+    with col2:
+        if st.checkbox("Scatter matrix"):
+            num_cols = df.select_dtypes(include="number").columns.tolist()[:6]  # limit to first 6
+            fig = px.scatter_matrix(df[num_cols], dimensions=num_cols, title="Scatter Matrix")
+            st.plotly_chart(fig, use_container_width=True)
+    with col3:
+        if st.checkbox("Correlation heatmap"):
+            corr = df.select_dtypes(include="number").corr()
+            fig, ax = plt.subplots(figsize=(6, 5))
+            im = ax.imshow(corr, vmin=-1, vmax=1, cmap="RdBu")
+            plt.xticks(range(len(corr)), corr.columns, rotation=45, ha="right")
+            plt.yticks(range(len(corr)), corr.columns)
+            plt.colorbar(im, ax=ax)
+            st.pyplot(fig)
+
+    # ── Trend & Forecast ──────────────────────────────────────────────────────
+    st.markdown("---")
+    st.markdown("### 📈 Trend & Forecast")
+    # pick date/time column
+    dt_cols = df.columns[df.dtypes.isin([np.dtype("datetime64[ns]"), np.dtype("object")])].tolist()
+    date_col = st.selectbox("Select date/time column", dt_cols)
+    df[date_col] = pd.to_datetime(df[date_col], errors="coerce")
+
+    # pick numeric metric
+    num_cols = df.select_dtypes(include="number").columns.tolist()
+    metric_col = st.selectbox("Select numeric metric", num_cols)
+
+    # prepare time series
+    ts = df[[date_col, metric_col]].dropna()
+    ts = ts.set_index(date_col).sort_index()
+    ts = ts[~ts.index.duplicated(keep="first")]
+
+    # Trend plot
+    fig_trend = px.line(ts, y=metric_col, title=f"{metric_col} over Time")
+    st.plotly_chart(fig_trend, use_container_width=True)
+
+    # Forecast next 90 days with ARIMA
+    with st.spinner("Running 90-day forecast…"):
         try:
-            df[col] = pd.to_datetime(df[col])
-        except: pass
-
-DATE_COL = st.selectbox("Date column", [c for c in df.columns if pd.api.types.is_datetime64_any_dtype(df[c])])
-NUM_COL = st.selectbox("Numeric metric", [c for c in df.select_dtypes("number").columns])
-
-ts = df[[DATE_COL, NUM_COL]].dropna().groupby(DATE_COL)[NUM_COL].mean().sort_index()
-fig_tr = px.line(ts, title=f"{NUM_COL} Trend", labels={"index":"Date", NUM_COL:NUM_COL})
-st.plotly_chart(fig_tr, use_container_width=True)
-
-# ───────────────────── 5 · ARIMA FORECAST ───────────────────
-st.subheader("🔮 ARIMA Forecast")
-steps = st.slider("Horizon (days)", 3, 365, 90)
-p = st.number_input("p", 0, 5, 1); d = st.number_input("d", 0, 2, 1); q = st.number_input("q", 0, 5, 1)
-try:
-    model = ARIMA(ts, order=(p, d, q)).fit()
-    future_idx = pd.date_range(ts.index[-1], periods=steps + 1, freq=pd.infer_freq(ts.index) or "D")[1:]
-    forecast = pd.Series(model.forecast(steps), index=future_idx, name="Forecast")
-    fig_fc = px.line(pd.concat([ts, forecast], axis=1), title="Actual vs Forecast")
-    st.plotly_chart(fig_fc, use_container_width=True)
-except Exception as e:
-    st.error(f"ARIMA failed: {e}")
-
-# ───────────────────── 6 · EDA EXPANDERS ────────────────────
-st.subheader("🔍 EDA Dashboard")
-with st.expander("Histogram + Box"):
-    st.plotly_chart(px.histogram(df, x=NUM_COL, marginal="box", template="plotly_dark"), use_container_width=True)
-with st.expander("Correlation Heatmap"):
-    corr = df.select_dtypes("number").corr()
-    st.plotly_chart(px.imshow(corr, color_continuous_scale="RdBu", title="Correlation"), use_container_width=True)
-
-# ───────────────────── 7 · STRATEGY BRIEF ───────────────────
-brief = (
-    "# Strategy Brief\n"
-    "• Clean missing date values for stable models.\n"
-    "• Investigate high correlations for driver analysis.\n"
-    "• Use forecast for inventory & workforce planning.\n"
-    "• Monitor outliers (>3σ) weekly.\n"
-    "• Segment by region/product for targeted actions."
-)
-st.download_button("⬇️ Download Strategy (.md)", brief, "bizintel_brief.md", "text/markdown")
+            model = ARIMA(ts, order=(1, 1, 1)).fit()
+            fcast = model.get_forecast(90)
+            idx = pd.date_range(ts.index.max(), periods=91, freq="D")[1:]
+            df_f = pd.DataFrame({"forecast": fcast.predicted_mean}, index=idx)
+
+            fig_fc = px.line(
+                pd.concat([ts, df_f], axis=1),
+                labels={metric_col: metric_col, "forecast": "Forecast"},
+                title=f"{metric_col} & 90-Day Forecast",
+            )
+            st.plotly_chart(fig_fc, use_container_width=True)
+        except Exception as e:
+            st.error(f"Forecast failed: {e}")
+
+    # ── Strategy Recommendations ─────────────────────────────────────────────
+    st.markdown("---")
+    st.markdown("### 🚀 Strategy Recommendations")
+    st.markdown(
+        """
+1. **Data Quality First**  
+   Address any missing or malformed dates before further time-series analysis.
+
+2. **Trend & Seasonality**  
+   Investigate any upward/downward trends and repeating seasonal patterns.
+
+3. **Outlier Management**  
+   Identify extreme highs/lows in your metric—could be bulk orders or data errors.
+
+4. **Segment-Level Analysis**  
+   Drill into key dimensions (e.g. region, product) to tailor growth strategies.
+
+5. **Predict & Act**  
+   Use your 90-day forecasts to guide inventory, staffing, and marketing decisions.
+        """
+    )
+
+    # downloadable strategy as markdown
+    strategy_md = st.session_state.get("strategy_md", "")
+    if not strategy_md:
+        strategy_md = st.session_state["strategy_md"] = st.container().markdown("…")  # dummy to store
+
+    st.download_button(
+        "📥 Download Strategy (.md)",
+        data="""
+# BizIntel AI Ultra – Strategy Recommendations
+
+1. Data Quality First: …
+2. Trend & Seasonality: …
+3. Outlier Management: …
+4. Segment-Level Analysis: …
+5. Predict & Act: …
+""",
+        file_name="strategy.md",
+        mime="text/markdown",
+    )