Spaces:
Build error
Build error
app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,487 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import numpy as np
|
| 4 |
+
import seaborn as sns
|
| 5 |
+
import matplotlib.pyplot as plt
|
| 6 |
+
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler, MinMaxScaler, RobustScaler
|
| 7 |
+
from sklearn.impute import KNNImputer
|
| 8 |
+
from scipy import stats
|
| 9 |
+
import plotly.express as px
|
| 10 |
+
import plotly.graph_objects as go
|
| 11 |
+
from plotly.subplots import make_subplots
|
| 12 |
+
import warnings
|
| 13 |
+
import io
|
| 14 |
+
import base64
|
| 15 |
+
from datetime import datetime
|
| 16 |
+
import json
|
| 17 |
+
import statsmodels.api as sm
|
| 18 |
+
from statsmodels.stats.outliers_influence import variance_inflation_factor
|
| 19 |
+
from scipy.stats import chi2_contingency
|
| 20 |
+
|
| 21 |
+
warnings.filterwarnings('ignore')
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
class DataAnalyzer:
|
| 25 |
+
def __init__(self):
|
| 26 |
+
self.df = None
|
| 27 |
+
self.numeric_columns = None
|
| 28 |
+
self.categorical_columns = None
|
| 29 |
+
|
| 30 |
+
def load_data(self, file):
|
| 31 |
+
try:
|
| 32 |
+
self.df = pd.read_csv(file.name)
|
| 33 |
+
self._identify_column_types()
|
| 34 |
+
return "Veri başarıyla yüklendi!"
|
| 35 |
+
except Exception as e:
|
| 36 |
+
return f"Hata: {str(e)}"
|
| 37 |
+
|
| 38 |
+
def _identify_column_types(self):
|
| 39 |
+
self.numeric_columns = self.df.select_dtypes(include=[np.number]).columns
|
| 40 |
+
self.categorical_columns = self.df.select_dtypes(include=['object']).columns
|
| 41 |
+
|
| 42 |
+
def get_basic_info(self):
|
| 43 |
+
if self.df is None:
|
| 44 |
+
return "Önce veri yükleyin!"
|
| 45 |
+
|
| 46 |
+
info = []
|
| 47 |
+
info.append("### 1. Temel Veri Bilgileri")
|
| 48 |
+
info.append(f"Satır Sayısı: {self.df.shape[0]}")
|
| 49 |
+
info.append(f"Sütun Sayısı: {self.df.shape[1]}")
|
| 50 |
+
|
| 51 |
+
memory_usage = self.df.memory_usage(deep=True).sum()
|
| 52 |
+
info.append(f"Bellek Kullanımı: {memory_usage / 1024:.2f} KB")
|
| 53 |
+
|
| 54 |
+
# Veri tipleri
|
| 55 |
+
info.append("\n### 2. Veri Tipleri ve Örnekler")
|
| 56 |
+
for column in self.df.columns:
|
| 57 |
+
unique_count = self.df[column].nunique()
|
| 58 |
+
info.append(f"\n{column}:")
|
| 59 |
+
info.append(f" - Tip: {self.df[column].dtype}")
|
| 60 |
+
info.append(f" - Benzersiz Değer Sayısı: {unique_count}")
|
| 61 |
+
info.append(f" - İlk 3 Örnek: {', '.join(map(str, self.df[column].head(3)))}")
|
| 62 |
+
|
| 63 |
+
return "\n".join(info)
|
| 64 |
+
|
| 65 |
+
def analyze_missing_values(self):
|
| 66 |
+
if self.df is None:
|
| 67 |
+
return "Önce veri yükleyin!"
|
| 68 |
+
|
| 69 |
+
missing = pd.DataFrame({
|
| 70 |
+
'Eksik Sayı': self.df.isnull().sum(),
|
| 71 |
+
'Eksik Yüzde': (self.df.isnull().sum() / len(self.df) * 100).round(2)
|
| 72 |
+
})
|
| 73 |
+
|
| 74 |
+
# Eksik değer pattern analizi
|
| 75 |
+
missing_patterns = self.df.isnull().value_counts().head()
|
| 76 |
+
|
| 77 |
+
result = "### Eksik Değer Analizi\n\n"
|
| 78 |
+
result += missing.to_string()
|
| 79 |
+
result += "\n\n### Eksik Değer Örüntüleri (İlk 5)\n\n"
|
| 80 |
+
result += missing_patterns.to_string()
|
| 81 |
+
|
| 82 |
+
return result
|
| 83 |
+
|
| 84 |
+
def analyze_outliers(self, method='zscore', threshold=3):
|
| 85 |
+
if self.df is None:
|
| 86 |
+
return "Önce veri yükleyin!"
|
| 87 |
+
|
| 88 |
+
results = []
|
| 89 |
+
results.append("### Aykırı Değer Analizi\n")
|
| 90 |
+
|
| 91 |
+
for column in self.numeric_columns:
|
| 92 |
+
results.append(f"\n{column} analizi:")
|
| 93 |
+
|
| 94 |
+
if method == 'zscore':
|
| 95 |
+
z_scores = np.abs(stats.zscore(self.df[column].dropna()))
|
| 96 |
+
outliers = np.where(z_scores > threshold)[0]
|
| 97 |
+
results.append(f"Z-score metodu ile {len(outliers)} aykırı değer bulundu")
|
| 98 |
+
if len(outliers) > 0:
|
| 99 |
+
results.append(f"Aykırı değerler: {self.df[column].iloc[outliers].values[:5]}...")
|
| 100 |
+
|
| 101 |
+
elif method == 'iqr':
|
| 102 |
+
Q1 = self.df[column].quantile(0.25)
|
| 103 |
+
Q3 = self.df[column].quantile(0.75)
|
| 104 |
+
IQR = Q3 - Q1
|
| 105 |
+
outliers = self.df[(self.df[column] < (Q1 - 1.5 * IQR)) |
|
| 106 |
+
(self.df[column] > (Q3 + 1.5 * IQR))][column]
|
| 107 |
+
results.append(f"IQR metodu ile {len(outliers)} aykırı değer bulundu")
|
| 108 |
+
if len(outliers) > 0:
|
| 109 |
+
results.append(f"Aykırı değerler: {outliers.values[:5]}...")
|
| 110 |
+
|
| 111 |
+
# Temel istatistikler
|
| 112 |
+
stats_data = self.df[column].describe()
|
| 113 |
+
results.append("\nTemel İstatistikler:")
|
| 114 |
+
results.append(stats_data.to_string())
|
| 115 |
+
|
| 116 |
+
return "\n".join(results)
|
| 117 |
+
|
| 118 |
+
def analyze_correlations(self):
|
| 119 |
+
if self.df is None:
|
| 120 |
+
return "Önce veri yükleyin!"
|
| 121 |
+
|
| 122 |
+
# Sayısal değişkenler için korelasyon
|
| 123 |
+
numeric_corr = self.df[self.numeric_columns].corr()
|
| 124 |
+
|
| 125 |
+
# Kategorik değişkenler için Cramer's V
|
| 126 |
+
cat_correlations = []
|
| 127 |
+
for col1 in self.categorical_columns:
|
| 128 |
+
for col2 in self.categorical_columns:
|
| 129 |
+
if col1 < col2:
|
| 130 |
+
contingency = pd.crosstab(self.df[col1], self.df[col2])
|
| 131 |
+
chi2, _, _, _ = chi2_contingency(contingency)
|
| 132 |
+
n = contingency.sum().sum()
|
| 133 |
+
v = np.sqrt(chi2 / (n * min(contingency.shape[0] - 1, contingency.shape[1] - 1)))
|
| 134 |
+
cat_correlations.append(f"{col1} - {col2}: {v:.3f}")
|
| 135 |
+
|
| 136 |
+
result = "### Sayısal Değişkenler Arası Korelasyonlar\n\n"
|
| 137 |
+
result += numeric_corr.round(3).to_string()
|
| 138 |
+
|
| 139 |
+
if cat_correlations:
|
| 140 |
+
result += "\n\n### Kategorik Değişkenler Arası İlişkiler (Cramer's V)\n\n"
|
| 141 |
+
result += "\n".join(cat_correlations)
|
| 142 |
+
|
| 143 |
+
return result
|
| 144 |
+
|
| 145 |
+
def create_visualization(self, plot_type, x_col, y_col=None, color_col=None):
|
| 146 |
+
if self.df is None:
|
| 147 |
+
return None
|
| 148 |
+
|
| 149 |
+
plt.figure(figsize=(10, 6))
|
| 150 |
+
|
| 151 |
+
try:
|
| 152 |
+
if plot_type == 'histogram':
|
| 153 |
+
fig = px.histogram(self.df, x=x_col, color=color_col,
|
| 154 |
+
title=f'{x_col} Histogram')
|
| 155 |
+
|
| 156 |
+
elif plot_type == 'box':
|
| 157 |
+
fig = px.box(self.df, x=x_col, y=y_col, color=color_col,
|
| 158 |
+
title=f'{x_col} - {y_col} Box Plot')
|
| 159 |
+
|
| 160 |
+
elif plot_type == 'scatter':
|
| 161 |
+
fig = px.scatter(self.df, x=x_col, y=y_col, color=color_col,
|
| 162 |
+
title=f'{x_col} vs {y_col} Scatter Plot')
|
| 163 |
+
|
| 164 |
+
elif plot_type == 'bar':
|
| 165 |
+
fig = px.bar(self.df, x=x_col, y=y_col, color=color_col,
|
| 166 |
+
title=f'{x_col} - {y_col} Bar Plot')
|
| 167 |
+
|
| 168 |
+
elif plot_type == 'violin':
|
| 169 |
+
fig = px.violin(self.df, x=x_col, y=y_col, color=color_col,
|
| 170 |
+
title=f'{x_col} - {y_col} Violin Plot')
|
| 171 |
+
|
| 172 |
+
elif plot_type == 'line':
|
| 173 |
+
fig = px.line(self.df, x=x_col, y=y_col, color=color_col,
|
| 174 |
+
title=f'{x_col} - {y_col} Line Plot')
|
| 175 |
+
|
| 176 |
+
elif plot_type == 'heatmap':
|
| 177 |
+
corr = self.df[[x_col, y_col]].corr()
|
| 178 |
+
fig = px.imshow(corr, title='Correlation Heatmap')
|
| 179 |
+
|
| 180 |
+
return fig
|
| 181 |
+
|
| 182 |
+
except Exception as e:
|
| 183 |
+
return f"Görselleştirme oluşturulurken hata: {str(e)}"
|
| 184 |
+
|
| 185 |
+
def feature_importance(self, target_col):
|
| 186 |
+
if self.df is None:
|
| 187 |
+
return "Önce veri yükleyin!"
|
| 188 |
+
|
| 189 |
+
try:
|
| 190 |
+
# Sayısal değişkenler için VIF hesaplama
|
| 191 |
+
X = self.df[self.numeric_columns].drop(columns=[target_col], errors='ignore')
|
| 192 |
+
vif_data = pd.DataFrame()
|
| 193 |
+
vif_data["Feature"] = X.columns
|
| 194 |
+
vif_data["VIF"] = [variance_inflation_factor(X.values, i)
|
| 195 |
+
for i in range(X.shape[1])]
|
| 196 |
+
|
| 197 |
+
result = "### Özellik Önem Analizi\n\n"
|
| 198 |
+
result += "VIF (Variance Inflation Factor) Değerleri:\n"
|
| 199 |
+
result += vif_data.sort_values('VIF', ascending=False).to_string()
|
| 200 |
+
|
| 201 |
+
# Korelasyon bazlı özellik önemi
|
| 202 |
+
if target_col in self.df.columns:
|
| 203 |
+
correlations = self.df[self.numeric_columns].corrwith(self.df[target_col])
|
| 204 |
+
result += "\n\nHedef Değişken ile Korelasyonlar:\n"
|
| 205 |
+
result += correlations.sort_values(ascending=False).to_string()
|
| 206 |
+
|
| 207 |
+
return result
|
| 208 |
+
|
| 209 |
+
except Exception as e:
|
| 210 |
+
return f"Özellik önem analizi sırasında hata: {str(e)}"
|
| 211 |
+
|
| 212 |
+
def statistical_tests(self, column1, column2=None):
|
| 213 |
+
if self.df is None:
|
| 214 |
+
return "Önce veri yükleyin!"
|
| 215 |
+
|
| 216 |
+
results = []
|
| 217 |
+
results.append("### İstatistiksel Test Sonuçları\n")
|
| 218 |
+
|
| 219 |
+
try:
|
| 220 |
+
# Tek değişkenli testler
|
| 221 |
+
if column2 is None:
|
| 222 |
+
# Normallik testi
|
| 223 |
+
stat, p_value = stats.normaltest(self.df[column1].dropna())
|
| 224 |
+
results.append(f"Normallik Testi (D'Agostino and Pearson's):")
|
| 225 |
+
results.append(f"Stat: {stat:.4f}, p-value: {p_value:.4f}")
|
| 226 |
+
results.append(f"Sonuç: {'Normal dağılım' if p_value > 0.05 else 'Normal dağılım değil'}\n")
|
| 227 |
+
|
| 228 |
+
# Temel istatistikler
|
| 229 |
+
desc = self.df[column1].describe()
|
| 230 |
+
results.append("Temel İstatistikler:")
|
| 231 |
+
results.append(desc.to_string())
|
| 232 |
+
|
| 233 |
+
# İki değişkenli testler
|
| 234 |
+
else:
|
| 235 |
+
if column1 in self.numeric_columns and column2 in self.numeric_columns:
|
| 236 |
+
# Pearson korelasyon
|
| 237 |
+
corr, p_value = stats.pearsonr(self.df[column1].dropna(),
|
| 238 |
+
self.df[column2].dropna())
|
| 239 |
+
results.append(f"Pearson Korelasyon:")
|
| 240 |
+
results.append(f"Correlation: {corr:.4f}, p-value: {p_value:.4f}\n")
|
| 241 |
+
|
| 242 |
+
# T-test
|
| 243 |
+
t_stat, p_value = stats.ttest_ind(self.df[column1].dropna(),
|
| 244 |
+
self.df[column2].dropna())
|
| 245 |
+
results.append(f"Bağımsız T-test:")
|
| 246 |
+
results.append(f"T-stat: {t_stat:.4f}, p-value: {p_value:.4f}\n")
|
| 247 |
+
|
| 248 |
+
elif column1 in self.categorical_columns and column2 in self.categorical_columns:
|
| 249 |
+
# Chi-square test
|
| 250 |
+
contingency = pd.crosstab(self.df[column1], self.df[column2])
|
| 251 |
+
chi2, p_value, dof, expected = chi2_contingency(contingency)
|
| 252 |
+
results.append(f"Chi-square Bağımsızlık Testi:")
|
| 253 |
+
results.append(f"Chi2: {chi2:.4f}, p-value: {p_value:.4f}")
|
| 254 |
+
|
| 255 |
+
return "\n".join(results)
|
| 256 |
+
|
| 257 |
+
except Exception as e:
|
| 258 |
+
return f"İstatistiksel testler sırasında hata: {str(e)}"
|
| 259 |
+
|
| 260 |
+
|
| 261 |
+
def create_interface():
|
| 262 |
+
analyzer = DataAnalyzer()
|
| 263 |
+
|
| 264 |
+
with gr.Blocks() as demo:
|
| 265 |
+
gr.Markdown("# Gelişmiş Veri Analiz Aracı")
|
| 266 |
+
|
| 267 |
+
with gr.Tab("Veri Yükleme ve Temel Bilgiler"):
|
| 268 |
+
file_input = gr.File(label="CSV Dosyası Yükleyin")
|
| 269 |
+
load_button = gr.Button("Veri Yükle")
|
| 270 |
+
info_button = gr.Button("Temel Bilgileri Göster")
|
| 271 |
+
output_text = gr.Textbox(label="Sonuçlar", lines=20)
|
| 272 |
+
|
| 273 |
+
load_button.click(analyzer.load_data, inputs=[file_input], outputs=[output_text])
|
| 274 |
+
info_button.click(analyzer.get_basic_info, outputs=[output_text])
|
| 275 |
+
|
| 276 |
+
with gr.Tab("Eksik Değer Analizi"):
|
| 277 |
+
missing_button = gr.Button("Eksik Değerleri Analiz Et")
|
| 278 |
+
missing_output = gr.Textbox(label="Eksik Değer Analizi", lines=15)
|
| 279 |
+
|
| 280 |
+
missing_button.click(analyzer.analyze_missing_values, outputs=[missing_output])
|
| 281 |
+
|
| 282 |
+
with gr.Tab("Aykırı Değer Analizi"):
|
| 283 |
+
with gr.Row():
|
| 284 |
+
outlier_method = gr.Radio(["zscore", "iqr"], label="Analiz Metodu", value="zscore")
|
| 285 |
+
outlier_threshold = gr.Slider(minimum=1, maximum=5, value=3, label="Eşik Değeri")
|
| 286 |
+
outlier_button = gr.Button("Aykırı Değerleri Analiz Et")
|
| 287 |
+
outlier_output = gr.Textbox(label="Aykırı Değer Analizi", lines=15)
|
| 288 |
+
|
| 289 |
+
outlier_button.click(
|
| 290 |
+
analyzer.analyze_outliers,
|
| 291 |
+
inputs=[outlier_method, outlier_threshold],
|
| 292 |
+
outputs=[outlier_output]
|
| 293 |
+
)
|
| 294 |
+
|
| 295 |
+
with gr.Tab("Korelasyon Analizi"):
|
| 296 |
+
corr_button = gr.Button("Korelasyonları Analiz Et")
|
| 297 |
+
corr_output = gr.Textbox(label="Korelasyon Analizi", lines=15)
|
| 298 |
+
|
| 299 |
+
corr_button.click(analyzer.analyze_correlations, outputs=[corr_output])
|
| 300 |
+
|
| 301 |
+
with gr.Tab("Görselleştirme"):
|
| 302 |
+
with gr.Row():
|
| 303 |
+
plot_type = gr.Dropdown(
|
| 304 |
+
choices=[
|
| 305 |
+
"histogram", "box", "scatter", "bar",
|
| 306 |
+
"violin", "line", "heatmap"
|
| 307 |
+
],
|
| 308 |
+
label="Grafik Tipi",
|
| 309 |
+
value="histogram"
|
| 310 |
+
)
|
| 311 |
+
x_col = gr.Dropdown(label="X Ekseni")
|
| 312 |
+
y_col = gr.Dropdown(label="Y Ekseni")
|
| 313 |
+
color_col = gr.Dropdown(label="Renk Değişkeni (Opsiyonel)")
|
| 314 |
+
|
| 315 |
+
plot_button = gr.Button("Grafik Oluştur")
|
| 316 |
+
plot_output = gr.Plot(label="Görselleştirme")
|
| 317 |
+
|
| 318 |
+
def update_columns(file):
|
| 319 |
+
if file is not None:
|
| 320 |
+
df = pd.read_csv(file.name)
|
| 321 |
+
return gr.Dropdown(choices=df.columns.tolist()), \
|
| 322 |
+
gr.Dropdown(choices=df.columns.tolist()), \
|
| 323 |
+
gr.Dropdown(choices=['None'] + df.columns.tolist())
|
| 324 |
+
return gr.Dropdown(), gr.Dropdown(), gr.Dropdown()
|
| 325 |
+
|
| 326 |
+
file_input.change(
|
| 327 |
+
update_columns,
|
| 328 |
+
inputs=[file_input],
|
| 329 |
+
outputs=[x_col, y_col, color_col]
|
| 330 |
+
)
|
| 331 |
+
|
| 332 |
+
plot_button.click(
|
| 333 |
+
analyzer.create_visualization,
|
| 334 |
+
inputs=[plot_type, x_col, y_col, color_col],
|
| 335 |
+
outputs=[plot_output]
|
| 336 |
+
)
|
| 337 |
+
|
| 338 |
+
with gr.Tab("İstatistiksel Analizler"):
|
| 339 |
+
with gr.Row():
|
| 340 |
+
stat_col1 = gr.Dropdown(label="Birinci Değişken")
|
| 341 |
+
stat_col2 = gr.Dropdown(label="İkinci Değişken (Opsiyonel)")
|
| 342 |
+
|
| 343 |
+
stat_button = gr.Button("İstatistiksel Testleri Çalıştır")
|
| 344 |
+
stat_output = gr.Textbox(label="Test Sonuçları", lines=15)
|
| 345 |
+
|
| 346 |
+
file_input.change(
|
| 347 |
+
lambda file: (
|
| 348 |
+
gr.Dropdown(choices=pd.read_csv(file.name).columns.tolist()),
|
| 349 |
+
gr.Dropdown(choices=['None'] + pd.read_csv(file.name).columns.tolist())
|
| 350 |
+
) if file else (gr.Dropdown(), gr.Dropdown()),
|
| 351 |
+
inputs=[file_input],
|
| 352 |
+
outputs=[stat_col1, stat_col2]
|
| 353 |
+
)
|
| 354 |
+
|
| 355 |
+
stat_button.click(
|
| 356 |
+
analyzer.statistical_tests,
|
| 357 |
+
inputs=[stat_col1, stat_col2],
|
| 358 |
+
outputs=[stat_output]
|
| 359 |
+
)
|
| 360 |
+
|
| 361 |
+
with gr.Tab("Özellik Önem Analizi"):
|
| 362 |
+
target_col = gr.Dropdown(label="Hedef Değişken")
|
| 363 |
+
importance_button = gr.Button("Özellik Önemini Analiz Et")
|
| 364 |
+
importance_output = gr.Textbox(label="Özellik Önem Analizi", lines=15)
|
| 365 |
+
|
| 366 |
+
file_input.change(
|
| 367 |
+
lambda file: gr.Dropdown(
|
| 368 |
+
choices=pd.read_csv(file.name).columns.tolist()) if file else gr.Dropdown(),
|
| 369 |
+
inputs=[file_input],
|
| 370 |
+
outputs=[target_col]
|
| 371 |
+
)
|
| 372 |
+
|
| 373 |
+
importance_button.click(
|
| 374 |
+
analyzer.feature_importance,
|
| 375 |
+
inputs=[target_col],
|
| 376 |
+
outputs=[importance_output]
|
| 377 |
+
)
|
| 378 |
+
|
| 379 |
+
with gr.Tab("Veri Ön İşleme"):
|
| 380 |
+
with gr.Row():
|
| 381 |
+
preprocess_method = gr.Radio(
|
| 382 |
+
choices=["standardization", "minmax", "robust", "log"],
|
| 383 |
+
label="Ölçeklendirme Metodu",
|
| 384 |
+
value="standardization"
|
| 385 |
+
)
|
| 386 |
+
columns_to_process = gr.Dropdown(
|
| 387 |
+
label="İşlenecek Sütunlar",
|
| 388 |
+
multiselect=True
|
| 389 |
+
)
|
| 390 |
+
|
| 391 |
+
def preprocess_data(file, method, columns):
|
| 392 |
+
if file is None:
|
| 393 |
+
return "Önce veri yükleyin!"
|
| 394 |
+
|
| 395 |
+
try:
|
| 396 |
+
df = pd.read_csv(file.name)
|
| 397 |
+
processed_df = df.copy()
|
| 398 |
+
|
| 399 |
+
if method == "standardization":
|
| 400 |
+
scaler = StandardScaler()
|
| 401 |
+
elif method == "minmax":
|
| 402 |
+
scaler = MinMaxScaler()
|
| 403 |
+
elif method == "robust":
|
| 404 |
+
scaler = RobustScaler()
|
| 405 |
+
elif method == "log":
|
| 406 |
+
for col in columns:
|
| 407 |
+
processed_df[col] = np.log1p(df[col])
|
| 408 |
+
return processed_df
|
| 409 |
+
|
| 410 |
+
if method != "log":
|
| 411 |
+
processed_df[columns] = scaler.fit_transform(df[columns])
|
| 412 |
+
|
| 413 |
+
output_path = "preprocessed_data.csv"
|
| 414 |
+
processed_df.to_csv(output_path, index=False)
|
| 415 |
+
return output_path
|
| 416 |
+
|
| 417 |
+
except Exception as e:
|
| 418 |
+
return f"Ön işleme sırasında hata: {str(e)}"
|
| 419 |
+
|
| 420 |
+
preprocess_button = gr.Button("Ön İşleme Uygula")
|
| 421 |
+
preprocess_output = gr.File(label="İşlenmiş Veri")
|
| 422 |
+
|
| 423 |
+
file_input.change(
|
| 424 |
+
lambda file: gr.Dropdown(
|
| 425 |
+
choices=pd.read_csv(file.name).select_dtypes(include=[np.number]).columns.tolist(),
|
| 426 |
+
multiselect=True
|
| 427 |
+
) if file else gr.Dropdown(),
|
| 428 |
+
inputs=[file_input],
|
| 429 |
+
outputs=[columns_to_process]
|
| 430 |
+
)
|
| 431 |
+
|
| 432 |
+
preprocess_button.click(
|
| 433 |
+
preprocess_data,
|
| 434 |
+
inputs=[file_input, preprocess_method, columns_to_process],
|
| 435 |
+
outputs=[preprocess_output]
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
with gr.Tab("Rapor Oluşturma"):
|
| 439 |
+
report_button = gr.Button("Kapsamlı Rapor Oluştur")
|
| 440 |
+
|
| 441 |
+
def generate_report(file):
|
| 442 |
+
if file is None:
|
| 443 |
+
return "Önce veri yükleyin!"
|
| 444 |
+
|
| 445 |
+
try:
|
| 446 |
+
analyzer.load_data(file)
|
| 447 |
+
|
| 448 |
+
report = []
|
| 449 |
+
report.append("# Veri Analiz Raporu")
|
| 450 |
+
report.append(f"Oluşturma Tarihi: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
|
| 451 |
+
|
| 452 |
+
report.append("## 1. Temel Bilgiler")
|
| 453 |
+
report.append(analyzer.get_basic_info())
|
| 454 |
+
|
| 455 |
+
report.append("\n## 2. Eksik Değer Analizi")
|
| 456 |
+
report.append(analyzer.analyze_missing_values())
|
| 457 |
+
|
| 458 |
+
report.append("\n## 3. Aykırı Değer Analizi")
|
| 459 |
+
report.append(analyzer.analyze_outliers())
|
| 460 |
+
|
| 461 |
+
report.append("\n## 4. Korelasyon Analizi")
|
| 462 |
+
report.append(analyzer.analyze_correlations())
|
| 463 |
+
|
| 464 |
+
# Raporu kaydet
|
| 465 |
+
report_text = "\n".join(report)
|
| 466 |
+
with open("data_analysis_report.txt", "w", encoding="utf-8") as f:
|
| 467 |
+
f.write(report_text)
|
| 468 |
+
|
| 469 |
+
return "data_analysis_report.txt"
|
| 470 |
+
|
| 471 |
+
except Exception as e:
|
| 472 |
+
return f"Rapor oluşturma sırasında hata: {str(e)}"
|
| 473 |
+
|
| 474 |
+
report_output = gr.File(label="Oluşturulan Rapor")
|
| 475 |
+
|
| 476 |
+
report_button.click(
|
| 477 |
+
generate_report,
|
| 478 |
+
inputs=[file_input],
|
| 479 |
+
outputs=[report_output]
|
| 480 |
+
)
|
| 481 |
+
|
| 482 |
+
return demo
|
| 483 |
+
|
| 484 |
+
# Arayüzü oluştur ve başlat
|
| 485 |
+
if __name__ == "__main__":
|
| 486 |
+
demo = create_interface()
|
| 487 |
+
demo.launch()
|