Spaces:
Sleeping
Sleeping
File size: 4,260 Bytes
2f99a1c |
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 |
import gradio as gr
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.impute import SimpleImputer
from io import BytesIO
import warnings
warnings.filterwarnings("ignore")
# Function to read and process uploaded file
def read_file(file):
if file.name.endswith(".csv"):
df = pd.read_csv(file)
elif file.name.endswith(".xlsx"):
df = pd.read_excel(file)
else:
raise ValueError("Unsupported file format. Please upload a CSV or Excel file.")
return df
# Clean the data
def clean_data(df):
# Drop duplicates
df = df.drop_duplicates()
# Fill missing values
imputer = SimpleImputer(strategy="most_frequent")
df = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
return df
# Generate summary statistics
def generate_summary(df):
return df.describe(include="all").transpose()
# Correlation heatmap
def generate_correlation_heatmap(df):
numeric_df = df.select_dtypes(include=[np.number])
corr = numeric_df.corr()
plt.figure(figsize=(10, 8))
sns.heatmap(corr, annot=True, cmap="coolwarm", fmt=".2f")
buf = BytesIO()
plt.savefig(buf, format="png")
buf.seek(0)
plt.close()
return buf
# Feature importance using Random Forest
def feature_importance(df):
# Encode categorical variables
df_encoded = df.copy()
label_encoders = {}
for col in df_encoded.select_dtypes(include="object").columns:
le = LabelEncoder()
df_encoded[col] = le.fit_transform(df_encoded[col])
label_encoders[col] = le
# Target variable selection
target_column = df_encoded.columns[-1]
X = df_encoded.iloc[:, :-1]
y = df_encoded[target_column]
# Fit Random Forest
model = RandomForestClassifier(random_state=42)
model.fit(X, y)
# Get feature importance
importance = pd.DataFrame({
"Feature": X.columns,
"Importance": model.feature_importances_
}).sort_values(by="Importance", ascending=False)
return importance
# Visualize feature importance
def plot_feature_importance(importance):
plt.figure(figsize=(10, 6))
sns.barplot(x="Importance", y="Feature", data=importance)
plt.title("Feature Importance")
buf = BytesIO()
plt.savefig(buf, format="png")
buf.seek(0)
plt.close()
return buf
# Main analysis function
def analyze_file(file):
try:
# Step 1: Read file
df = read_file(file)
# Step 2: Clean data
df_cleaned = clean_data(df)
# Step 3: Generate summary statistics
summary = generate_summary(df_cleaned)
# Step 4: Generate correlation heatmap
heatmap_buf = generate_correlation_heatmap(df_cleaned)
# Step 5: Feature importance analysis
importance = feature_importance(df_cleaned)
importance_plot_buf = plot_feature_importance(importance)
# Step 6: Return results
return (
summary,
heatmap_buf,
importance.head(10), # Top 10 important features
importance_plot_buf,
)
except Exception as e:
return str(e)
# Gradio Interface
def gradio_interface():
with gr.Blocks() as interface:
gr.Markdown("# AI Data Analytics Tool")
gr.Markdown("Upload your dataset in CSV or Excel format to analyze and generate insights automatically.")
with gr.Row():
file_input = gr.File(label="Upload your CSV or Excel file")
analyze_button = gr.Button("Analyze")
with gr.Row():
summary_output = gr.Dataframe(label="Summary Statistics")
heatmap_output = gr.Image(label="Correlation Heatmap")
importance_output = gr.Dataframe(label="Feature Importance")
importance_plot_output = gr.Image(label="Feature Importance Plot")
analyze_button.click(
analyze_file,
inputs=file_input,
outputs=[summary_output, heatmap_output, importance_output, importance_plot_output],
)
return interface
# Launch the Gradio interface
interface = gradio_interface()
interface.launch(debug=True)
|