Michael
35ea21ad33
Add shared hide_streamlit_chrome() helper that removes header bar, hamburger menu, footer, and deploy button via CSS injection. Called on every page. Add .streamlit/config.toml with minimal toolbar mode. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
140 lines
4.2 KiB
Python
140 lines
4.2 KiB
Python
"""DataTools — Data Cleaning Mastery Suite.
|
|
|
|
Launch:
|
|
streamlit run src/gui/app.py
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import streamlit as st
|
|
|
|
# Ensure project root is on sys.path so `src.core` imports work
|
|
_project_root = Path(__file__).resolve().parent.parent.parent
|
|
if str(_project_root) not in sys.path:
|
|
sys.path.insert(0, str(_project_root))
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Page config
|
|
# ---------------------------------------------------------------------------
|
|
|
|
from src.gui.components import hide_streamlit_chrome
|
|
|
|
st.set_page_config(
|
|
page_title="DataTools — Data Cleaning Mastery",
|
|
page_icon="🧹",
|
|
layout="wide",
|
|
)
|
|
|
|
hide_streamlit_chrome()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Home page
|
|
# ---------------------------------------------------------------------------
|
|
|
|
st.title("🧹 DataTools — Data Cleaning Mastery")
|
|
st.caption("A 9-tool suite for cleaning, standardizing, and validating tabular data. Runs 100% locally.")
|
|
|
|
st.divider()
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tool cards
|
|
# ---------------------------------------------------------------------------
|
|
|
|
TOOLS = [
|
|
{
|
|
"icon": "🔍",
|
|
"name": "Deduplicator",
|
|
"description": "Fuzzy matching, normalization, survivor selection, and interactive review.",
|
|
"status": "Ready",
|
|
"page": "1_Deduplicator",
|
|
},
|
|
{
|
|
"icon": "✂️",
|
|
"name": "Text Cleaner",
|
|
"description": "Whitespace trim, multi-space collapse, Unicode normalization, BOM and line-ending handling.",
|
|
"status": "Coming Soon",
|
|
"page": "2_Text_Cleaner",
|
|
},
|
|
{
|
|
"icon": "📐",
|
|
"name": "Format Standardizer",
|
|
"description": "Standardize dates, currencies, names, phone numbers, and addresses.",
|
|
"status": "Coming Soon",
|
|
"page": "3_Format_Standardizer",
|
|
},
|
|
{
|
|
"icon": "🕳️",
|
|
"name": "Missing Value Handler",
|
|
"description": "Detect disguised nulls, missingness analysis, and imputation strategies.",
|
|
"status": "Coming Soon",
|
|
"page": "4_Missing_Values",
|
|
},
|
|
{
|
|
"icon": "🗂️",
|
|
"name": "Column Mapper",
|
|
"description": "Rename columns, enforce a target schema, and coerce types.",
|
|
"status": "Coming Soon",
|
|
"page": "5_Column_Mapper",
|
|
},
|
|
{
|
|
"icon": "📊",
|
|
"name": "Outlier Detector",
|
|
"description": "Z-score, IQR, and MAD detection with domain-rule violations and winsorization.",
|
|
"status": "Coming Soon",
|
|
"page": "6_Outlier_Detector",
|
|
},
|
|
{
|
|
"icon": "📎",
|
|
"name": "Multi-File Merger",
|
|
"description": "Combine multiple CSV/Excel files with schema alignment.",
|
|
"status": "Coming Soon",
|
|
"page": "7_Multi_File_Merger",
|
|
},
|
|
{
|
|
"icon": "✅",
|
|
"name": "Validator & Reporter",
|
|
"description": "Validate against rules and generate PDF/Excel quality reports.",
|
|
"status": "Coming Soon",
|
|
"page": "8_Validator_Reporter",
|
|
},
|
|
{
|
|
"icon": "⚙️",
|
|
"name": "Pipeline Runner",
|
|
"description": "Chain tools in recommended order and pass output between steps.",
|
|
"status": "Coming Soon",
|
|
"page": "9_Pipeline_Runner",
|
|
},
|
|
]
|
|
|
|
# Render tool cards in a 3-column grid
|
|
for row_start in range(0, len(TOOLS), 3):
|
|
cols = st.columns(3)
|
|
for i, col in enumerate(cols):
|
|
idx = row_start + i
|
|
if idx >= len(TOOLS):
|
|
break
|
|
tool = TOOLS[idx]
|
|
with col:
|
|
status_color = "green" if tool["status"] == "Ready" else "orange"
|
|
st.markdown(
|
|
f"### {tool['icon']} {tool['name']}\n\n"
|
|
f"{tool['description']}\n\n"
|
|
f":{status_color}[**{tool['status']}**]"
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Footer
|
|
# ---------------------------------------------------------------------------
|
|
|
|
st.divider()
|
|
st.caption(
|
|
"Runs locally. Your data never leaves this computer. "
|
|
"| DataTools v3.0"
|
|
)
|