File size: 6,176 Bytes
bf6b618
 
 
 
 
 
 
 
 
5fa5a4a
 
 
bf6b618
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import pandas as pd
import io
import re
import yaml
from typing import List, Optional
from fastapi import FastAPI, File, UploadFile, HTTPException, Query
from fastapi.responses import JSONResponse
import uvicorn
from fastapi.middleware.cors import CORSMiddleware

app = FastAPI()

# Carregar configuração
with open("column_config.yaml") as f:
    COLUMN_CONFIG = yaml.safe_load(f)

# Função para detectar tipos de colunas
def detect_column_type(dtype):
    if pd.api.types.is_datetime64_any_dtype(dtype):
        return "datetime"
    elif pd.api.types.is_numeric_dtype(dtype):
        return "number"
    return "text"

# Normalização de colunas
def normalize_column_names(column_names: List[str]) -> List[str]:
    normalized = []
    for raw_col in column_names:
        sanitized = re.sub(r'[\W]+', '_', raw_col.strip()).lower().strip('_')
        for config_col, config in COLUMN_CONFIG['columns'].items():
            synonyms = [
                re.sub(r'[\W]+', '_', s.strip()).lower().strip('_')
                for s in [config_col] + config.get('synonyms', [])
            ]
            if sanitized in synonyms:
                normalized.append(config_col)
                break
        else:
            normalized.append(sanitized)
    return normalized

# Limpeza de dados aprimorada
def clean_data(df: pd.DataFrame) -> pd.DataFrame:
    df.columns = normalize_column_names(df.columns)

    # Tratamento de valores ausentes
    for col in df.columns:
        if col in COLUMN_CONFIG['columns']:
            col_type = COLUMN_CONFIG['columns'][col].get('type', 'text')
            if col_type == 'datetime':
                df[col] = pd.to_datetime(df[col], errors='coerce')
            elif col_type == 'numeric':
                df[col] = pd.to_numeric(df[col], errors='coerce')
            elif col_type == 'categorical':
                allowed = COLUMN_CONFIG['columns'][col].get('allowed', [])
                df[col] = df[col].where(df[col].isin(allowed), None)

    # Tratamento de formatos inconsistentes
    for col in df.columns:
        if col in COLUMN_CONFIG['columns']:
            col_type = COLUMN_CONFIG['columns'][col].get('type', 'text')
            if col_type == 'datetime':
                fmt = COLUMN_CONFIG['columns'][col].get('format')
                df[col] = pd.to_datetime(df[col], errors='coerce', format=fmt)
                df[col] = df[col].dt.strftime('%Y-%m-%dT%H:%M:%SZ')
            elif col_type == 'numeric':
                df[col] = pd.to_numeric(df[col], errors='coerce').astype(float)
            elif col_type == 'categorical':
                allowed = COLUMN_CONFIG['columns'][col].get('allowed', [])
                df[col] = df[col].where(df[col].isin(allowed))

    # Tratamento de outliers
    for col in df.columns:
        if col in COLUMN_CONFIG['columns']:
            col_type = COLUMN_CONFIG['columns'][col].get('type', 'text')
            if col_type == 'numeric':
                q1 = df[col].quantile(0.25)
                q3 = df[col].quantile(0.75)
                iqr = q3 - q1
                lower_bound = q1 - 1.5 * iqr
                upper_bound = q3 + 1.5 * iqr
                df[col] = df[col].clip(lower=lower_bound, upper=upper_bound)

    # Tratamento de registros duplicados
    df.drop_duplicates(inplace=True)

    # Tratamento de tipos de dados mistos
    for col in df.columns:
        if col in COLUMN_CONFIG['columns']:
            col_type = COLUMN_CONFIG['columns'][col].get('type', 'text')
            if col_type == 'numeric':
                df[col] = pd.to_numeric(df[col], errors='coerce')
            elif col_type == 'datetime':
                df[col] = pd.to_datetime(df[col], errors='coerce')

    # Tratamento de dados ruídos
    for col in df.columns:
        if col in COLUMN_CONFIG['columns']:
            col_type = COLUMN_CONFIG['columns'][col].get('type', 'text')
            if col_type == 'text':
                df[col] = df[col].str.strip().str.lower()

    return df.replace({pd.NA: None})

# Função para processar o arquivo e retornar dados limpos
def process_file(file: UploadFile, sheet_name: Optional[str] = None) -> pd.DataFrame:
    try:
        content = file.file.read()
        extension = file.filename.split('.')[-1]
        if extension == 'csv':
            df = pd.read_csv(io.BytesIO(content))
        elif extension == 'xlsx':
            if sheet_name is None:
                sheet_name = 0  # Default to the first sheet
            df = pd.read_excel(io.BytesIO(content), sheet_name=sheet_name)
        else:
            raise HTTPException(400, "Formato de arquivo não suportado")
        return df, clean_data(df)
    except Exception as e:
        raise HTTPException(500, f"Erro ao processar o arquivo: {str(e)}")

# Endpoint para upload e processamento de arquivos
@app.post("/process-file")
async def process_file_endpoint(file: UploadFile = File(...), sheet_name: Optional[str] = Query(None)):
    try:
        raw_df, df = process_file(file, sheet_name)

        columns = [{
            "name": col,
            "type": detect_column_type(df[col].dtype)
        } for col in df.columns]

        rows = []
        for idx, row in df.iterrows():
            cells = {}
            for col, val in row.items():
                cells[col] = {
                    "value": val,
                    "displayValue": str(val),
                    "columnId": col
                }
            rows.append({"id": str(idx), "cells": cells})

        return JSONResponse(
            content={
                "data": {
                    "columns": columns,
                    "rows": rows
                },
                "metadata": {
                    "totalRows": len(df),
                    "processedAt": pd.Timestamp.now().isoformat()
                }
            })
    except Exception as e:
        raise HTTPException(500, f"Erro: {str(e)}")

# Configuração de CORS
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

if __name__ == "__main__":
    uvicorn.run("app:app", host="0.0.0.0", port=7860, reload=True)