File size: 2,699 Bytes
1dcbe02 79c5ac1 1dcbe02 79c5ac1 1dcbe02 79c5ac1 1dcbe02 79c5ac1 1dcbe02 79c5ac1 1dcbe02 |
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 |
import gradio as gr
import pandas as pd
import os
import zipfile
def process_csv(uploaded_file):
"""
Process the uploaded CSV file to:
1. Replace text-based columns and numerical columns with less than six unique options with coded values.
2. Fill missing values in numerical columns with their respective medians.
3. Return a zip file containing the modified CSV file, a legend CSV, and a CSV detailing data fill methods.
"""
# Load the data from the uploaded file's byte stream
data = pd.read_csv(uploaded_file.name)
# List to store mappings of columns
mapping_list = []
# List to store the details of columns where data was added
data_added_details = []
# Loop through each column in the DataFrame
for col in data.columns:
# Check if the column is of type object (text-based) or if it's numerical with less than six unique options
if data[col].dtype == 'object' or (data[col].nunique() < 6 and pd.api.types.is_numeric_dtype(data[col])):
# Create a mapping of original values to codes, including NaN or blank values mapped to -9999
mapping = {value: code if pd.notna(value) else -9999 for code, value in enumerate(data[col].unique())}
for original_value, mapped_value in mapping.items():
mapping_list.append([col, original_value, mapped_value])
# Replace the values in the column with their respective codes
data[col] = data[col].map(mapping)
elif pd.api.types.is_numeric_dtype(data[col]) and any(pd.isna(data[col])):
# Replace with median
median_value = data[col].median()
data[col].fillna(median_value, inplace=True)
data_added_details.append([col, "Median", median_value])
# Name of the zip file
zip_name = "processed_files.zip"
# Save CSV files and add them to the zip file
with zipfile.ZipFile(zip_name, 'w') as zipf:
data.to_csv("modified_data.csv", index=False)
zipf.write("modified_data.csv")
mapping_df = pd.DataFrame(mapping_list, columns=['Column', 'Original Value', 'Mapped Value'])
mapping_df.to_csv("mapping.csv", index=False)
zipf.write("mapping.csv")
data_added_df = pd.DataFrame(data_added_details, columns=['Column', 'Method', 'Value Added'])
data_added_df.to_csv("data_added_details.csv", index=False)
zipf.write("data_added_details.csv")
return zip_name
# Gradio Interface
iface = gr.Interface(
fn=process_csv,
inputs=gr.inputs.File(type="file", label="Upload CSV File"),
outputs=gr.outputs.File(label="Download Processed Files"),
live=False
)
iface.launch() |