2024_Ruthe_SND/code/statistical_analysis_of_quantitative_data.py

# -*- coding: utf-8 -*-
"""
Created on Fri Sep 27 13:19:08 2024

@author: arefks
"""
import os
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import statsmodels.formula.api as smf
from statsmodels.stats.multicomp import MultiComparison
from itertools import combinations
import statsmodels
import scipy
from scipy.stats import dunnett

# Set up warning suppression for convergence
import warnings
warnings.simplefilter(action='ignore')


# Get the directory where the code file is located
code_dir = os.path.dirname(os.path.abspath(__file__))

# Get the parent directory of the code directory
parent_dir = os.path.dirname(code_dir)

# Create a new folder for mixed model analysis
mixed_model_dir = os.path.join(parent_dir, 'output', "Quantitative_outputs", 'normality')
os.makedirs(mixed_model_dir, exist_ok=True)

# Step 4: Save the resulting dataframe to a CSV file
input_file_path = os.path.join(parent_dir, 'output', "Quantitative_outputs", 'Quantitative_results_from_dwi_processing.csv')
df_init = pd.read_csv(input_file_path)
# Filtering the dataframe based on conditions
df = df_init[~df_init["merged_timepoint"].isin([42, 56])]


# Iterate over unique values of "Qtype" and "mask_name"
#for qq in df["Qtype"].unique():
for qq in ["fa"]:
    for dd in df["dialation_amount"].unique():
        for mm in df["mask_name"].unique():
            # Filter the dataframe based on current "Qtype" and "mask_name"
            filtered_df = df[(df["Qtype"] == qq) & (df["mask_name"] == mm) & (df["dialation_amount"] == dd)]
            # Identify duplicates based on 'merged_timepoint' and 'subjectID'
            duplicates = filtered_df[filtered_df.duplicated(subset=['merged_timepoint', 'subjectID'], keep=False)]
            # Print the duplicates
            if not duplicates.empty:
                print("Duplicate subject ID and timepoint entries found:\n", duplicates)
            # Remove duplicates and store in a new DataFrame
            temp_df = filtered_df.drop_duplicates(subset=['merged_timepoint', 'subjectID'])


# Create a DataFrame from results
results_df = pd.DataFrame(results)

# Save results_df as CSV in mixed_model_analysis folder
output_file_path = os.path.join(mixed_model_dir, 'mixed_model_results.csv')
results_df.to_csv(output_file_path, index=False)

# Print the table
print(results_df)