Spaces:
Sleeping
Sleeping
File size: 9,760 Bytes
f2b2374 274299c f2b2374 274299c cb2cc09 f2b2374 cb2cc09 f2b2374 27ab62c f2b2374 274299c f2b2374 274299c f2b2374 b2607f4 f2b2374 274299c b2607f4 f2b2374 b2607f4 f2b2374 274299c b2607f4 274299c b2607f4 274299c b2607f4 f2b2374 b2607f4 274299c f2b2374 274299c b2607f4 274299c b2607f4 f2b2374 b2607f4 f2b2374 cfff021 cb2cc09 f2b2374 274299c f2b2374 4968d23 f2b2374 274299c 4968d23 274299c f2b2374 4968d23 274299c f2b2374 274299c f2b2374 4968d23 cb2cc09 274299c f2b2374 274299c f2b2374 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
from fastapi import FastAPI, UploadFile, File, HTTPException
from fastapi.responses import HTMLResponse, JSONResponse
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import pandas as pd
import openpyxl
import numpy as np
from sentence_transformers import SentenceTransformer
from typing import List
import io
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_methods=["*"],
allow_headers=["*"]
)
model = SentenceTransformer('all-MiniLM-L6-v2')
HTML_CONTENT = """
<!DOCTYPE html>
<html>
<head>
<title>Analytics Dashboard</title>
<script src="https://unpkg.com/react@18/umd/react.development.js"></script>
<script src="https://unpkg.com/react-dom@18/umd/react-dom.development.js"></script>
<script src="https://unpkg.com/recharts@2.1.9/umd/Recharts.js"></script>
<script src="https://unpkg.com/@babel/standalone/babel.min.js"></script>
<script src="https://cdn.tailwindcss.com"></script>
</head>
<body>
<div id="root"></div>
<script type="text/babel">
function App() {
const [file, setFile] = React.useState(null);
const [data, setData] = React.useState(null);
const [query, setQuery] = React.useState('');
const [insights, setInsights] = React.useState([]);
const [loading, setLoading] = React.useState(false);
const [error, setError] = React.useState(null);
const handleFileChange = (event) => {
setFile(event.target.files[0]);
setError(null);
};
const handleUpload = async () => {
if (!file) return;
setLoading(true);
setError(null);
const formData = new FormData();
formData.append('file', file);
try {
const response = await fetch('/api/process-file', {
method: 'POST',
body: formData,
});
if (!response.ok) {
const error = await response.json();
throw new Error(error.detail || 'Upload failed');
}
const result = await response.json();
setData(result);
} catch (err) {
setError(err.message);
} finally {
setLoading(false);
}
};
const handleQuery = async () => {
if (!data || !query) return;
setLoading(true);
try {
const response = await fetch('/api/query', {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({query, embeddings: data.embeddings})
});
if (!response.ok) throw new Error('Query failed');
const result = await response.json();
setInsights(result.similar_indices.map(idx => data.raw_data[idx]));
} catch (err) {
setError(err.message);
} finally {
setLoading(false);
}
};
return (
<div className="p-6 max-w-6xl mx-auto">
<h1 className="text-3xl font-bold mb-8">Data Analytics Dashboard</h1>
{error && (
<div className="bg-red-100 border border-red-400 text-red-700 px-4 py-3 rounded mb-4">
{error}
</div>
)}
<div className="space-y-4">
<div className="flex flex-col gap-2">
<input
type="file"
onChange={handleFileChange}
accept=".xlsx,.csv"
className="block w-full text-sm border rounded p-2"
disabled={loading}
/>
<button
onClick={handleUpload}
disabled={!file || loading}
className="bg-blue-500 text-white px-4 py-2 rounded disabled:opacity-50"
>
{loading ? 'Processing...' : 'Upload'}
</button>
</div>
{data && (
<div className="space-y-4">
<div className="flex gap-2">
<input
type="text"
value={query}
onChange={(e) => setQuery(e.target.value)}
placeholder="Ask a question about your data..."
className="flex-1 p-2 border rounded"
disabled={loading}
/>
<button
onClick={handleQuery}
className="px-4 py-2 bg-blue-600 text-white rounded hover:bg-blue-700 disabled:opacity-50"
disabled={loading || !query}
>
Search
</button>
</div>
{insights.length > 0 && (
<div className="mt-8">
<h3 className="text-xl font-semibold mb-4">Related Insights</h3>
<div className="grid gap-4">
{insights.map((insight, idx) => (
<div key={idx} className="p-4 bg-gray-50 rounded shadow">
{Object.entries(insight).map(([key, value]) => (
<div key={key} className="mb-1">
<span className="font-medium">{key}:</span>{' '}
{value}
</div>
))}
</div>
))}
</div>
</div>
)}
</div>
)}
</div>
</div>
);
}
ReactDOM.render(<App />, document.getElementById('root'));
</script>
</body>
</html>
"""
class QueryRequest(BaseModel):
query: str
embeddings: List[List[float]]
@app.get("/")
async def root():
return HTMLResponse(HTML_CONTENT)
@app.post("/api/process-file")
async def process_file(file: UploadFile = File(...)):
if not file.filename:
raise HTTPException(status_code=400, detail="No file provided")
try:
contents = await file.read()
if file.filename.endswith('.xlsx'):
wb = openpyxl.load_workbook(io.BytesIO(contents), read_only=True)
sheet = wb.active
data = []
headers = next(sheet.rows)
header_values = [cell.value for cell in headers]
for row in sheet.rows:
if row != headers:
data.append({h: cell.value for h, cell in zip(header_values, row)})
df = pd.DataFrame(data)
elif file.filename.endswith('.csv'):
df = pd.read_csv(io.BytesIO(contents))
else:
raise HTTPException(status_code=400, detail="Unsupported file type")
# Convert timestamps to strings
for col in df.select_dtypes(include=['datetime64[ns]']).columns:
df[col] = df[col].astype(str)
df = df.replace({np.nan: None})
text_reps = [" ".join(f"{col}: {str(val)}" for col, val in row.items() if val is not None)
for _, row in df.iterrows()]
embeddings = model.encode(text_reps)
# Convert DataFrame to JSON-serializable format
raw_data = df.to_dict('records')
# Convert any non-serializable types to strings
for record in raw_data:
for key, value in record.items():
if not isinstance(value, (str, int, float, bool, type(None))):
record[key] = str(value)
return JSONResponse({
'embeddings': embeddings.tolist(),
'metadata': {
'columns': list(df.columns),
'row_count': len(df)
},
'raw_data': raw_data
})
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.post("/api/query")
async def query_data(request: QueryRequest):
try:
query_embedding = model.encode([request.query])[0]
similarities = np.dot(request.embeddings, query_embedding)
return JSONResponse({"similar_indices": np.argsort(similarities)[-5:][::-1].tolist()})
except Exception as e:
raise HTTPException(status_code=500, detail=str(e)) |