2024_Ruthe_SND/output/Final_Quantitative_output/add_grouping.py

import pandas as pd

# Load the first CSV file
df = pd.read_csv(r"E:\2024_Ruthe_SND\output\Final_Quantitative_output\data_summary.csv")

# Load the second CSV file
cluster_df = pd.read_csv("C:\\Users\\aswen\\Desktop\\Code\\Behavioural_analysis\\output\\final_zscored_clustered.csv")

# Merge the 'Sham' column from cluster_df to df based on 'subjectID' and 'Study ID'
df = df.merge(cluster_df[['Study ID', 'Sham']], left_on='subjectID', right_on='Study ID', how='left')

# Rename 'Sham' column to 'Group' and replace True/False values with 'sham'/'Stroke'
df['Group'] = df['Sham'].apply(lambda x: 'sham' if x == True else 'Stroke')


# Save the updated DataFrame to a new CSV file
output_file_path = r"E:\2024_Ruthe_SND\output\Final_Quantitative_output\Quantitative_output_adjusted.csv"
df.to_csv(output_file_path, index=False)

print("Adjusted results saved successfully at:", output_file_path)