app.py

# app.py  —  BizIntel AI Ultra  (CSV, Excel, DB; Plotly, Gemini 1.5 Pro)

import os
import tempfile
from io import StringIO
from typing import Literal

import pandas as pd
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

# ──────────────────────────────────────────────────────────────
# 1.  GEMINI 1.5‑PRO
# ──────────────────────────────────────────────────────────────
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"},
)

# ──────────────────────────────────────────────────────────────
# 2.  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, or DB)
# ──────────────────────────────────────────────────────────────
source = st.radio("Select data source", ["Upload CSV / Excel", "Connect to SQL Database"])

csv_path: str | None = None
file_type: Literal["csv", "excel"] | None = None

if source == "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"
            try:
                df_excel = pd.read_excel(temp_path, sheet_name=0)  # loads first sheet
                csv_path = os.path.splitext(temp_path)[0] + ".csv"
                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 ✅")

else:  # SQL DB
    engine = st.selectbox("DB engine", SUPPORTED_ENGINES)
    conn = st.text_input("SQLAlchemy connection string")
    if conn:
        try:
            tbls = list_tables(conn)
            tbl = st.selectbox("Table", tbls)
            if st.button("Fetch table"):
                csv_path = fetch_data_from_db(conn, tbl)
                file_type = "csv"
                st.success(f"Fetched **{tbl}** as CSV ✅")
        except Exception as e:
            st.error(f"Connection failed: {e}")
            st.stop()

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
# ──────────────────────────────────────────────────────────────
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
# ──────────────────────────────────────────────────────────────
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)
else:
    st.warning(sales_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

if forecast_png:
    st.image(forecast_png, caption="Sales Forecast", use_column_width=True)

# ──────────────────────────────────────────────────────────────
# 6.  GEMINI STRATEGY
# ──────────────────────────────────────────────────────────────
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"
    "3. Risk factors or anomalies\n"
    "4. Suggested additional visuals\n"
)

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")

# ──────────────────────────────────────────────────────────────
# 7.  KPI CARDS + EXPANDER
# ──────────────────────────────────────────────────────────────
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

st.markdown("---")
st.subheader("📑 Dataset Overview")
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,
    )

# ──────────────────────────────────────────────────────────────
# 8.  OPTIONAL EXPLORATORY VISUALS
# ──────────────────────────────────────────────────────────────
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)

if st.checkbox("Scatter‑matrix"):
    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)