File to play with long and wide format

Example.py

# ---
# jupyter:
#   jupytext:
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.10.3
#   kernelspec:
#     display_name: Python 3.8.7 64-bit
#     metadata:
#       interpreter:
#         hash: 719f0e7d5e00575541adf0654af7819dee753b35cdfdf7b361adc0a54809f9ea
#     name: python3
# ---

# %%
import pandas as pd
import string
import numpy as np
import random
import matplotlib.pyplot as plt

def generate_example_dataframe()-> pd.DataFrame:
    """
    This simple function will generate simple dataframe in long format 
    """
    num = 20 # number of regions udsed in simulations
    subjects_num = 10
    random.seed(1)
    conditions = ["open", "closed"]
    groups = ["old", "young"]
    means = [1,1.5,1.25,1.75]
    regions = [f"region_{s}" for s in string.ascii_letters[:num]]
    subjects = [f"subject_{s}" for s in list(range(1, subjects_num))]

    list_of_dataframes = []
    for subject in subjects:
        for region in regions:
            lst = iter(means)
            for condition in conditions:
                for group in groups:
                    mean = next(lst)
                    values = mean + np.random.rand(num) + 0.2*random.random()
                    temp_df = pd.DataFrame({'region':[region] *num, 'group':[group] * num, 'condition':[condition] *num ,'subject':[subject] *num ,'values':values})
                    list_of_dataframes.append(temp_df)

    return pd.concat(list_of_dataframes)



# %% [markdown]
# Genereting sample dataframe is presented in the long format - one obe

# %%
df = generate_example_dataframe()
df.head()

# %%
# big region 
# joining dataframes


lobesList = ["parietal", "frontal", "temporal", "occipital"]
lobes = random.choices(LobesList, k=len(pd.unique(df.region)))
lobe_info= pd.DataFrame({'region':pd.unique(df.region),'lobe':lobes})
df = pd.merge(df, lobe_info, on='region')

print(df.columns.values.tolist())


# %%
index_list=  ["lobe"]

conditions = ['group', 'condition', 'subject']

values = ['values']


# %%
groupdf =  df.groupby(index_list + conditions)[values].mean()
groupdf = groupdf.reset_index()
groupdf.head()

# %%
print(df.columns.values.tolist())


# %%
pivoted = df.pivot_table(index=["subject"], 
                    columns=['group', 'condition', 'lobe'], 
                    values=values)  
pivoted.columns = pivoted.columns.map(''.join)
pivoted = pivoted.reset_index()
pivoted.head()



# %%

ages = np.random.randint(20,70,len(pd.unique(df.subject)))
age_info = pd.DataFrame({'subject':pd.unique(df.subject),'age':ages})
pivoted = pd.merge(pivoted, age_info, on='subject')

plt.plot(pivoted.age, pivoted.valuesoldclosedfrontal, 'ro')

# %%