Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
import numpy as np
|
4 |
+
from transformers import pipeline
|
5 |
+
from sklearn.impute import SimpleImputer
|
6 |
+
from sklearn.ensemble import IsolationForest
|
7 |
+
import subprocess
|
8 |
+
import sys
|
9 |
+
|
10 |
+
# التحقق من تثبيت PyTorch أو TensorFlow
|
11 |
+
try:
|
12 |
+
import torch
|
13 |
+
except ImportError:
|
14 |
+
print("PyTorch غير مثبت، سيتم تثبيته الآن.")
|
15 |
+
subprocess.check_call([sys.executable, "-m", "pip", "install", "torch"])
|
16 |
+
|
17 |
+
try:
|
18 |
+
import tensorflow
|
19 |
+
except ImportError:
|
20 |
+
print("TensorFlow غير مثبت، سيتم تثبيته الآن.")
|
21 |
+
subprocess.check_call([sys.executable, "-m", "pip", "install", "tensorflow"])
|
22 |
+
|
23 |
+
# تحميل نموذج التلخيص من Hugging Face
|
24 |
+
summarizer = pipeline("summarization", model="t5-small")
|
25 |
+
|
26 |
+
def analyze_data_quality(file):
|
27 |
+
df = pd.read_csv(file.name)
|
28 |
+
|
29 |
+
# البحث عن القيم الناقصة
|
30 |
+
missing_values = df.isnull().sum()
|
31 |
+
missing_summary = missing_values[missing_values > 0].to_string()
|
32 |
+
|
33 |
+
# البحث عن القيم الشاذة باستخدام Isolation Forest
|
34 |
+
clf = IsolationForest(contamination=0.05, random_state=42)
|
35 |
+
outliers = clf.fit_predict(df.select_dtypes(include=[np.number]))
|
36 |
+
outlier_count = (outliers == -1).sum()
|
37 |
+
|
38 |
+
# تلخيص النتائج
|
39 |
+
report = f"🔍 تحليل جودة البيانات:\n\n"
|
40 |
+
report += f"📌 عدد القيم الناقصة: {missing_values.sum()}\n"
|
41 |
+
report += f"📌 عدد القيم الشاذة: {outlier_count}\n"
|
42 |
+
report += "\n📊 تفاصيل القيم الناقصة:\n" + missing_summary if missing_summary else "\n✅ لا توجد قيم ناقصة."
|
43 |
+
|
44 |
+
summary = summarizer(report, max_length=100, do_sample=False)[0]['summary_text']
|
45 |
+
|
46 |
+
return summary
|
47 |
+
|
48 |
+
def clean_data(file):
|
49 |
+
df = pd.read_csv(file.name)
|
50 |
+
|
51 |
+
# معالجة القيم الناقصة بالتعبئة
|
52 |
+
imputer = SimpleImputer(strategy="mean")
|
53 |
+
df[df.select_dtypes(include=[np.number]).columns] = imputer.fit_transform(df.select_dtypes(include=
|