Update app.py

app.py

@@ -1,203 +1,189 @@
-# app.py  —  BizIntel AI Ultra  
-# Supports: CSV/Excel/DB ingestion, date+metric plotting, ARIMA forecasting,
-# safe Plotly writes into /tmp, Gemini 1.5 Pro strategy, KPI cards, optional EDA.
-
-import os
-import tempfile
-
-import pandas as pd
 import streamlit as st
-import google.generativeai as genai
-import plotly.graph_objects as go
-
-# ──────────────────────────────────────────────────────────────
-# 0) Monkey‐patch Plotly to write images into /tmp (writable)
-# ──────────────────────────────────────────────────────────────
-TMP = tempfile.gettempdir()
-_orig_write = go.Figure.write_image
-def _safe_write(self, path, *args, **kwargs):
-    filename = os.path.basename(path)
-    safe_path = os.path.join(TMP, filename)
-    return _orig_write(self, safe_path, *args, **kwargs)
-go.Figure.write_image = _safe_write
-
-# ──────────────────────────────────────────────────────────────
-# 1) Tool & DB imports
-# ──────────────────────────────────────────────────────────────
-from tools.csv_parser      import parse_csv_tool
-from tools.plot_generator  import plot_metric_tool
-from tools.forecaster      import forecast_metric_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
-
-# ──────────────────────────────────────────────────────────────
-# 2) Gemini 1.5 Pro initialization
-# ──────────────────────────────────────────────────────────────
-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",
-    },
+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
+
+# ── 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",
+    layout="wide",
+    initial_sidebar_state="expanded",
 )
-
-# ──────────────────────────────────────────────────────────────
-# 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()
-
-# ──────────────────────────────────────────────────────────────
-# 4) Data source selection: CSV/Excel or SQL Database
-# ───────────────────────────────────���──────────────────────────
-source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
-csv_path = None
-
-if source == "Upload CSV / Excel":
-    upload = st.file_uploader("Upload CSV or Excel (≤ 500 MB)", type=["csv","xlsx","xls"])
-    if upload:
-        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 = tmp_file
-        else:
-            try:
-                df_xl = pd.read_excel(tmp_file, sheet_name=0)
-                csv_path = tmp_file.rsplit(".", 1)[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:
-    engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
-    conn   = st.text_input("SQLAlchemy connection string")
-    if conn:
+
+# ── Data source selection ───────────────────────────────────────────────────────
+data_source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])
+
+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,
+    )
+    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:
-            tables = list_tables(conn)
-            tbl    = st.selectbox("Table", tables)
-            if st.button("Fetch table"):
-                csv_path = fetch_data_from_db(conn, tbl)
-                st.success(f"Fetched **{tbl}** as CSV ✅")
+            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"Connection failed: {e}")
-            st.stop()
-
-if not csv_path:
-    st.stop()
-
-# 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))
-
-# ──────────────────────────────────────────────────────────────
-# 5) Show head & pick date + metric (but never the same column)
-# ──────────────────────────────────────────────────────────────
-df_head = pd.read_csv(csv_path, nrows=5)
-st.dataframe(df_head)
-
-# a) Date dropdown over all columns
-date_col = st.selectbox("Select date/time column", df_head.columns)
-
-# b) Metric dropdown only numeric columns, excluding the chosen date_col
-numeric_cols = df_head.select_dtypes("number").columns.tolist()
-metric_options = [c for c in numeric_cols if c != date_col]
-if not metric_options:
-    st.error(f"No numeric columns available once we exclude '{date_col}'.")
-    st.stop()
-metric_col = st.selectbox("Select numeric metric column", metric_options)
-
-# ──────────────────────────────────────────────────────────────
-# 6) Local analysis: summary, trend chart, forecast
-# ──────────────────────────────────────────────────────────────
-with st.spinner("Parsing dataset…"):
-    summary_text = parse_csv_tool(csv_path)
-
-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("Running forecast…"):
-    forecast_text = forecast_metric_tool(csv_path, date_col, metric_col)
-
-st.subheader(f"🔮 {metric_col} Forecast")
-forecast_png = os.path.join(TEMP_DIR, "forecast_plot.png")
-if os.path.exists(forecast_png):
-    st.image(forecast_png, use_container_width=True)
-else:
-    st.warning("Forecast image not found.")
-
-# ──────────────────────────────────────────────────────────────
-# 7) Gemini-driven strategy recommendations
-# ──────────────────────────────────────────────────────────────
-prompt = (
-    f"You are **BizIntel Strategist AI**.\n\n"
-    f"### Dataset Summary\n```\n{summary_text}\n```\n\n"
-    f"### {metric_col} Forecast\n```\n{forecast_text}\n```\n\n"
-    "Return **Markdown** with:\n"
-    "1. Five key insights\n"
-    "2. Three actionable strategies\n"
-    "3. Risk factors or anomalies\n"
-    "4. Suggested additional visuals\n"
-)
+            st.error(f"Forecast failed: {e}")
 
-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")
-
-# ──────────────────────────────────────────────────────────────
-# 8) KPI cards + detailed Stats
-# ────────────────────────────────────────────────────────��─────
-full_df     = pd.read_csv(csv_path, low_memory=False)
-total_rows  = len(full_df)
-num_columns = full_df.shape[1]
-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_columns))
-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
-    )
+    # ── 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.
 
-# ──────────────────────────────────────────────────────────────
-# 9) Optional Exploratory Visuals
-# ──────────────────────────────────────────────────────────────
-st.markdown("---")
-st.subheader("🔍 Optional Exploratory Visuals")
+3. **Outlier Management**  
+   Identify extreme highs/lows in your metric—could be bulk orders or data errors.
 
-if st.checkbox("Histogram"):
-    hcol = st.selectbox("Variable", numeric_cols, key="hist")
-    st.plotly_chart(histogram_tool(csv_path, hcol), use_container_width=True)
+4. **Segment-Level Analysis**  
+   Drill into key dimensions (e.g. region, product) to tailor growth strategies.
 
-if st.checkbox("Scatter Matrix"):
-    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)
+5. **Predict & Act**  
+   Use your 90-day forecasts to guide inventory, staffing, and marketing decisions.
+        """
+    )
 
-if st.checkbox("Correlation Heatmap"):
-    st.plotly_chart(corr_heatmap_tool(csv_path), use_container_width=True)
+    # 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",
+    )