Breadway/dotfiles
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update Fedora state: 2026-04-29 11:50

Browse source
This commit is contained in:
Breadway 2026-04-29 11:50:42 +08:00
parent 42ca768584
commit 10f0d5de1d
338 changed files with 18983 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

284
dot_config/private_Code/User/History/7da6e0fb/9KVj.py Normal file
View file

@ -0,0 +1,284 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_theme(style='whitegrid', context='talk')
def finish_plot(filename):
plt.tight_layout()
plt.savefig(outdir / filename, dpi=200, bbox_inches='tight')
if show_plots:
plt.show()
plt.close()
# 1) PRIMARY OUTCOME: Mean happiness by group with error bars and value labels
if 'Group' in df.columns:
plt.figure(figsize=(8, 6))
summary = df.groupby('Group')['Happiness'].agg(['mean', 'std', 'count']).reindex(['Control', 'Intervention'])
ci95 = 1.96 * (summary['std'] / np.sqrt(summary['count']))
bars = plt.bar(
np.arange(len(summary)),
summary['mean'].values,
yerr=ci95.values,
color=['#A9B2C3', '#4E79A7'],
capsize=8,
edgecolor='black',
linewidth=1.2,
alpha=0.9
)
plt.xticks(np.arange(len(summary)), ['Control Group\n(No habits tracked)', 'Intervention Group\n(Daily habits tracked)'])
plt.title('Effect of Tracked Organization Habits on Happiness', pad=15, fontsize=14, fontweight='bold')
plt.ylabel('Mean Daily Happiness Score (1-10)', fontsize=12)
plt.ylim(1, 10)
for bar in bars:
yval = bar.get_height()
plt.text(bar.get_x() + bar.get_width()/2, yval - 0.8, f'{yval:.1f}', ha='center', va='center', color='white', fontweight='bold', fontsize=11)
finish_plot('01_primary_outcome_group_comparison.png')
# 2) DISTRIBUTIONS: Show overlap and variability in happiness scores
if 'Group' in df.columns:
plt.figure(figsize=(9, 6))
order = ['Control', 'Intervention']
sns.violinplot(
data=df, x='Group', y='Happiness', order=order,
inner='quartile', palette={'Control': '#E0E0E0', 'Intervention': '#B3CDE3'}, cut=0
)
sns.stripplot(
data=df, x='Group', y='Happiness', order=order,
color='black', alpha=0.12, jitter=0.25, size=3
)
plt.title('Distribution of Happiness Reports Over 30 Days', pad=15, fontsize=14, fontweight='bold')
plt.xlabel('Study Group', fontsize=12)
plt.ylabel('Happiness Score', fontsize=12)
plt.ylim(1, 10)
finish_plot('02_happiness_distribution_by_group.png')
# 3) LONGITUDINAL: Daily happiness trend across 30 days
if 'Group' in df.columns and 'Day' in df.columns:
plt.figure(figsize=(10, 6))
daily_mean = df.groupby(['Group', 'Day'])['Happiness'].mean().reset_index()
sns.lineplot(
data=daily_mean, x='Day', y='Happiness', hue='Group',
hue_order=['Control', 'Intervention'],
palette={'Control': '#7F7F7F', 'Intervention': '#D62728'},
marker='o', linewidth=2.5, markersize=6
)
plt.title('Longitudinal Daily Happiness Throughout the Study', pad=15, fontsize=14, fontweight='bold')
plt.xlabel('Day of Study (1-30)', fontsize=12)
plt.ylabel('Average Happiness', fontsize=12)
plt.ylim(1, 10)
plt.xticks(range(1, 31, 2))
plt.legend(title='', frameon=True, facecolor='white', fontsize=10)
finish_plot('03_longitudinal_trends.png')
# 4) DOSE-RESPONSE: In intervention group, does MORE habits = MORE happiness?
intervention_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
plt.figure(figsize=(9, 6))
sns.boxplot(
data=intervention_df, x='Habits_Count', y='Happiness',
color='#9ECAE1', width=0.6, fliersize=0
)
sns.stripplot(
data=intervention_df, x='Habits_Count', y='Happiness',
color='#2B5B84', alpha=0.3, jitter=0.2, size=4
)
plt.title('Dose-Response: Happiness by Number of Habits Completed', pad=15, fontsize=14, fontweight='bold')
plt.xlabel('Number of Requested Habits Completed That Day\n(Calendar + Clean Room + Punctual)', fontsize=11)
plt.ylabel('Happiness Score', fontsize=12)
plt.ylim(1, 10)
finish_plot('04_habit_dose_response.png')
# 5) HABIT COMPLETION RATES: Which habits were easiest to maintain?
habit_cols = ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']
adherence_rates = intervention_df[habit_cols].mean().sort_values(ascending=False).reset_index()
adherence_rates.columns = ['Habit', 'Rate']
adherence_rates['Habit'] = adherence_rates['Habit'].str.replace('_Adherence', '', regex=False)
plt.figure(figsize=(8, 6))
bars = sns.barplot(data=adherence_rates, x='Habit', y='Rate', color='#E76F51')
plt.title('Which Habits Were Easiest to Keep?', pad=15, fontsize=14, fontweight='bold')
plt.xlabel('', fontsize=12)
plt.ylabel('Percentage of Days Completed', fontsize=12)
plt.ylim(0, 1.05)
plt.gca().yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1.0))
for bar in bars.patches:
plt.text(bar.get_x() + bar.get_width() / 2, bar.get_height() + 0.02,
f"{bar.get_height()*100:.0f}%", ha='center', va='bottom', fontweight='bold', fontsize=10)
finish_plot('05_habit_completion_rates.png')
# 6) INDIVIDUAL VARIATION: Participant-level averages show broad effect
if 'Group' in df.columns:
plt.figure(figsize=(12, 6))
participant_avg = df.groupby(['Group', 'Participant_ID'])['Happiness'].mean().reset_index()
participant_avg = participant_avg.sort_values(['Group', 'Happiness'])
participant_avg['Order_Index'] = range(len(participant_avg))
for group, color in zip(['Control', 'Intervention'], ['#BDBDBD', '#4E79A7']):
group_data = participant_avg[participant_avg['Group'] == group]
plt.bar(group_data['Order_Index'], group_data['Happiness'], color=color, label=group, alpha=0.85, width=0.8)
plt.axhline(df[df['Group']=='Control']['Happiness'].mean(), color='#7F7F7F', linestyle='--', linewidth=2, label='Control Mean')
plt.axhline(df[df['Group']=='Intervention']['Happiness'].mean(), color='#2B5B84', linestyle='--', linewidth=2, label='Intervention Mean')
plt.title('Individual Average Happiness Across Study Participants', pad=15, fontsize=14, fontweight='bold')
plt.xlabel('Individual Participants (Sorted by Happiness Level)', fontsize=12)
plt.ylabel('Average Happiness Score', fontsize=12)
plt.xticks([])
plt.ylim(1, 10)
plt.legend(frameon=True, facecolor='white', fontsize=10, loc='upper left')
finish_plot('06_individual_participant_avgs.png')
logging.info('Saved study plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

227
dot_config/private_Code/User/History/7da6e0fb/FOyN.py Normal file
View file

@ -0,0 +1,227 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(data=df, x='Habits_Count', y='Happiness', color='#4C72B0')
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(data=df, x='Habits_Count', y='Happiness', inner=None, color='#55A868')
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=range(len(participant_avg)), y=participant_avg.values, color='#C44E52')
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(range(len(participant_avg)), participant_avg.index, rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
if 'Group' in df.columns:
plt.figure(figsize=(7, 5))
sns.barplot(data=df, x='Group', y='Happiness', estimator='mean', errorbar='sd', color='#8172B2')
plt.title('Mean Happiness by Group')
plt.ylabel('Average happiness')
f_group = outdir / 'happiness_by_group.png'
plt.tight_layout()
plt.savefig(f_group)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
if 'Group' in df.columns:
sns.scatterplot(data=df, x='Habits_Count', y='Happiness', hue='Group', alpha=0.35)
else:
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

227
dot_config/private_Code/User/History/7da6e0fb/Gx76.py Normal file
View file

@ -0,0 +1,227 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(data=df, x='Habits_Count', y='Happiness', color='#4C72B0')
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(data=df, x='Habits_Count', y='Happiness', inner=None, color='#55A868')
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=range(len(participant_avg)), y=participant_avg.values, color='#C44E52')
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(range(len(participant_avg)), participant_avg.index.astype(str), rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
if 'Group' in df.columns:
plt.figure(figsize=(7, 5))
sns.barplot(data=df, x='Group', y='Happiness', estimator='mean', errorbar='sd', color='#8172B2')
plt.title('Mean Happiness by Group')
plt.ylabel('Average happiness')
f_group = outdir / 'happiness_by_group.png'
plt.tight_layout()
plt.savefig(f_group)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
if 'Group' in df.columns:
sns.scatterplot(data=df, x='Habits_Count', y='Happiness', hue='Group', alpha=0.35)
else:
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

253
dot_config/private_Code/User/History/7da6e0fb/Ldgu.py Normal file
View file

@ -0,0 +1,253 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_theme(style='whitegrid', context='talk')
def finish_plot(filename):
plt.tight_layout()
plt.savefig(outdir / filename, dpi=200, bbox_inches='tight')
if show_plots:
plt.show()
plt.close()
# 1) Mean happiness by group with error bars
if 'Group' in df.columns:
summary = df.groupby('Group')['Happiness'].agg(['mean', 'std', 'count']).reindex(['Control', 'Intervention'])
ci95 = 1.96 * (summary['std'] / np.sqrt(summary['count']))
plt.figure(figsize=(8, 6))
plt.bar(summary.index, summary['mean'], color=['#7A7A7A', '#2A9D8F'], yerr=ci95, capsize=6)
plt.title('Average Happiness by Group')
plt.xlabel('Study group')
plt.ylabel('Mean happiness score')
plt.ylim(0, 10)
finish_plot('01_mean_happiness_by_group.png')
# 2) Distribution of happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(9, 6))
order = ['Control', 'Intervention']
sns.boxplot(data=df, x='Group', y='Happiness', order=order, color='#C9D1D9')
sns.stripplot(data=df, x='Group', y='Happiness', order=order, color='black', alpha=0.18, jitter=0.22, size=2)
plt.title('Happiness Distribution by Group')
plt.xlabel('Study group')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('02_happiness_distribution_by_group.png')
# 3) Daily happiness trend by group
if 'Group' in df.columns and 'Day' in df.columns:
daily = df.groupby(['Group', 'Day'], as_index=False)['Happiness'].mean()
plt.figure(figsize=(10, 6))
sns.lineplot(data=daily, x='Day', y='Happiness', hue='Group', hue_order=['Control', 'Intervention'], marker='o')
plt.title('Mean Daily Happiness Across the Study')
plt.xlabel('Day of study')
plt.ylabel('Average happiness')
plt.ylim(0, 10)
plt.xticks(range(1, 31, 2))
finish_plot('03_daily_happiness_trend.png')
# 4) Happiness by number of habits in intervention group only
intervention_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
plt.figure(figsize=(9, 6))
sns.boxplot(data=intervention_df, x='Habits_Count', y='Happiness', color='#4C72B0')
sns.stripplot(data=intervention_df, x='Habits_Count', y='Happiness', color='black', alpha=0.20, jitter=0.18, size=2)
plt.title('Intervention Group: Happiness by Number of Habits Completed')
plt.xlabel('Habits completed that day')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('04_happiness_by_habits_intervention.png')
# 5) Mean happiness by habits count in intervention group
habits_mean = intervention_df.groupby('Habits_Count', as_index=False)['Happiness'].mean()
plt.figure(figsize=(8, 6))
sns.lineplot(data=habits_mean, x='Habits_Count', y='Happiness', marker='o', color='#1F77B4')
plt.title('Intervention Group: Mean Happiness vs Habits Completed')
plt.xlabel('Number of habits completed')
plt.ylabel('Mean happiness')
plt.xticks([0, 1, 2, 3])
plt.ylim(0, 10)
finish_plot('05_mean_happiness_by_habits.png')
# 6) Habit adherence rates in the intervention group
habit_cols = ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']
adherence_rates = intervention_df[habit_cols].mean().sort_values(ascending=False).reset_index()
adherence_rates.columns = ['Habit', 'Rate']
adherence_rates['Habit'] = adherence_rates['Habit'].str.replace('_Adherence', '', regex=False)
plt.figure(figsize=(9, 6))
sns.barplot(data=adherence_rates, x='Habit', y='Rate', color='#E76F51')
plt.title('Intervention Group: Habit Completion Rate')
plt.xlabel('Habit')
plt.ylabel('Proportion completed')
plt.ylim(0, 1)
plt.gca().yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1.0))
finish_plot('06_habit_completion_rate.png')
# 7) Participant average happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(12, 6))
participant_avg = df.groupby(['Group', 'Participant_ID'], as_index=False)['Happiness'].mean()
sns.boxplot(data=participant_avg, x='Group', y='Happiness', order=['Control', 'Intervention'], color='#D6D6D6')
sns.stripplot(data=participant_avg, x='Group', y='Happiness', order=['Control', 'Intervention'], color='black', alpha=0.45, jitter=0.12, size=5)
plt.title('Average Happiness per Participant')
plt.xlabel('Study group')
plt.ylabel('Participant mean happiness')
plt.ylim(0, 10)
finish_plot('07_participant_average_happiness.png')
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

272
dot_config/private_Code/User/History/7da6e0fb/MtI5.py Normal file
View file

@ -0,0 +1,272 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_theme(style='whitegrid', context='talk')
def finish_plot(filename):
plt.tight_layout()
plt.savefig(outdir / filename, dpi=200, bbox_inches='tight')
if show_plots:
plt.show()
plt.close()
# 1) Mean happiness by group with error bars
if 'Group' in df.columns:
plt.figure(figsize=(8, 6))
order = ['Control', 'Intervention']
sns.barplot(
data=df,
x='Group',
y='Happiness',
order=order,
estimator='mean',
errorbar=('ci', 95),
palette=['#7A7A7A', '#2A9D8F'],
)
plt.title('Average Happiness by Group')
plt.xlabel('Study group')
plt.ylabel('Mean happiness score')
plt.ylim(0, 10)
finish_plot('01_mean_happiness_by_group.png')
# 2) Distribution of happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(9, 6))
order = ['Control', 'Intervention']
sns.boxplot(data=df, x='Group', y='Happiness', order=order, palette=['#B0B0B0', '#73C6B6'])
sns.stripplot(data=df, x='Group', y='Happiness', order=order, color='black', alpha=0.18, jitter=0.22, size=2)
plt.title('Happiness Distribution by Group')
plt.xlabel('Study group')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('02_happiness_distribution_by_group.png')
# 3) Daily happiness trend by group
if 'Group' in df.columns and 'Day' in df.columns:
daily = df.groupby(['Group', 'Day'], as_index=False)['Happiness'].mean()
plt.figure(figsize=(10, 6))
sns.lineplot(data=daily, x='Day', y='Happiness', hue='Group', hue_order=['Control', 'Intervention'], marker='o')
plt.title('Mean Daily Happiness Across the Study')
plt.xlabel('Day of study')
plt.ylabel('Average happiness')
plt.ylim(0, 10)
plt.xticks(range(1, 31, 2))
finish_plot('03_daily_happiness_trend.png')
# 4) Happiness by number of habits in intervention group only
intervention_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
plt.figure(figsize=(9, 6))
sns.boxplot(data=intervention_df, x='Habits_Count', y='Happiness', color='#4C72B0')
sns.stripplot(data=intervention_df, x='Habits_Count', y='Happiness', color='black', alpha=0.20, jitter=0.18, size=2)
plt.title('Intervention Group: Happiness by Number of Habits Completed')
plt.xlabel('Habits completed that day')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('04_happiness_by_habits_intervention.png')
# 5) Mean happiness by habits count in intervention group
habits_mean = intervention_df.groupby('Habits_Count', as_index=False)['Happiness'].mean()
plt.figure(figsize=(8, 6))
sns.lineplot(data=habits_mean, x='Habits_Count', y='Happiness', marker='o', color='#1F77B4')
plt.title('Intervention Group: Mean Happiness vs Habits Completed')
plt.xlabel('Number of habits completed')
plt.ylabel('Mean happiness')
plt.xticks([0, 1, 2, 3])
plt.ylim(0, 10)
finish_plot('05_mean_happiness_by_habits.png')
# 6) Habit adherence rates in the intervention group
habit_cols = ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']
adherence_rates = (
intervention_df[habit_cols]
.mean()
.sort_values(ascending=False)
.reset_index()
.rename(columns={'index': 'Habit', 0: 'Rate'})
)
adherence_rates['Habit'] = adherence_rates['Habit'].str.replace('_Adherence', '', regex=False)
plt.figure(figsize=(9, 6))
sns.barplot(data=adherence_rates, x='Habit', y=0, color='#E76F51')
plt.title('Intervention Group: Habit Completion Rate')
plt.xlabel('Habit')
plt.ylabel('Proportion completed')
plt.ylim(0, 1)
plt.gca().yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1.0))
finish_plot('06_habit_completion_rate.png')
# 7) Participant averages, grouped by study group
if 'Group' in df.columns:
participant_avg = df.groupby(['Group', 'Participant_ID'])['Happiness'].mean().reset_index()
plt.figure(figsize=(12, 6))
sns.barplot(
data=participant_avg,
x='Participant_ID',
y='Happiness',
hue='Group',
dodge=True,
palette=['#7A7A7A', '#2A9D8F'],
)
plt.title('Average Happiness per Participant')
plt.xlabel('Participant ID')
plt.ylabel('Mean happiness')
plt.ylim(0, 10)
plt.xticks(rotation=45)
finish_plot('07_participant_average_happiness.png')
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

270
dot_config/private_Code/User/History/7da6e0fb/NtsI.py Normal file
View file

@ -0,0 +1,270 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_theme(style='whitegrid', context='talk')
def finish_plot(filename):
plt.tight_layout()
plt.savefig(outdir / filename, dpi=200, bbox_inches='tight')
if show_plots:
plt.show()
plt.close()
# 1) Mean happiness by group with error bars
if 'Group' in df.columns:
summary = df.groupby('Group')['Happiness'].agg(['mean', 'std', 'count']).reindex(['Control', 'Intervention'])
ci95 = 1.96 * (summary['std'] / np.sqrt(summary['count']))
plt.figure(figsize=(8, 6))
xpos = np.arange(len(summary))
plt.bar(xpos, summary['mean'].values, color=['#7A7A7A', '#2A9D8F'], yerr=ci95.values, capsize=6)
plt.xticks(xpos, summary.index)
plt.title('Average Happiness by Group')
plt.xlabel('Study group')
plt.ylabel('Mean happiness score')
plt.ylim(0, 10)
finish_plot('01_mean_happiness_by_group.png')
# 2) Distribution of happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(9, 6))
order = ['Control', 'Intervention']
grouped = [df.loc[df['Group'] == group, 'Happiness'].values for group in order]
plt.boxplot(grouped, labels=order, patch_artist=True,
boxprops=dict(facecolor='#C9D1D9', color='#4C4C4C'),
medianprops=dict(color='#2A9D8F', linewidth=2),
whiskerprops=dict(color='#4C4C4C'), capprops=dict(color='#4C4C4C'))
for i, group in enumerate(order, start=1):
y = df.loc[df['Group'] == group, 'Happiness'].values
x = np.random.normal(i, 0.06, size=len(y))
plt.scatter(x, y, color='black', alpha=0.15, s=10)
plt.title('Happiness Distribution by Group')
plt.xlabel('Study group')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('02_happiness_distribution_by_group.png')
# 3) Daily happiness trend by group
if 'Group' in df.columns and 'Day' in df.columns:
daily = df.groupby(['Group', 'Day'], as_index=False)['Happiness'].mean()
plt.figure(figsize=(10, 6))
sns.lineplot(data=daily, x='Day', y='Happiness', hue='Group', hue_order=['Control', 'Intervention'], marker='o')
plt.title('Mean Daily Happiness Across the Study')
plt.xlabel('Day of study')
plt.ylabel('Average happiness')
plt.ylim(0, 10)
plt.xticks(range(1, 31, 2))
finish_plot('03_daily_happiness_trend.png')
# 4) Happiness by number of habits in intervention group only
intervention_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
plt.figure(figsize=(9, 6))
sns.boxplot(data=intervention_df, x='Habits_Count', y='Happiness', color='#4C72B0')
sns.stripplot(data=intervention_df, x='Habits_Count', y='Happiness', color='black', alpha=0.20, jitter=0.18, size=2)
plt.title('Intervention Group: Happiness by Number of Habits Completed')
plt.xlabel('Habits completed that day')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('04_happiness_by_habits_intervention.png')
# 5) Mean happiness by habits count in intervention group
habits_mean = intervention_df.groupby('Habits_Count', as_index=False)['Happiness'].mean()
plt.figure(figsize=(8, 6))
sns.lineplot(data=habits_mean, x='Habits_Count', y='Happiness', marker='o', color='#1F77B4')
plt.title('Intervention Group: Mean Happiness vs Habits Completed')
plt.xlabel('Number of habits completed')
plt.ylabel('Mean happiness')
plt.xticks([0, 1, 2, 3])
plt.ylim(0, 10)
finish_plot('05_mean_happiness_by_habits.png')
# 6) Habit adherence rates in the intervention group
habit_cols = ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']
adherence_rates = intervention_df[habit_cols].mean().sort_values(ascending=False).reset_index()
adherence_rates.columns = ['Habit', 'Rate']
adherence_rates['Habit'] = adherence_rates['Habit'].str.replace('_Adherence', '', regex=False)
plt.figure(figsize=(9, 6))
sns.barplot(data=adherence_rates, x='Habit', y='Rate', color='#E76F51')
plt.title('Intervention Group: Habit Completion Rate')
plt.xlabel('Habit')
plt.ylabel('Proportion completed')
plt.ylim(0, 1)
plt.gca().yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1.0))
finish_plot('06_habit_completion_rate.png')
# 7) Participant average happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(12, 6))
participant_avg = df.groupby(['Group', 'Participant_ID'], as_index=False)['Happiness'].mean()
group_order = ['Control', 'Intervention']
grouped_avgs = [participant_avg.loc[participant_avg['Group'] == group, 'Happiness'].values for group in group_order]
plt.boxplot(grouped_avgs, labels=group_order, patch_artist=True,
boxprops=dict(facecolor='#D6D6D6', color='#4C4C4C'),
medianprops=dict(color='#2A9D8F', linewidth=2),
whiskerprops=dict(color='#4C4C4C'), capprops=dict(color='#4C4C4C'))
for i, group in enumerate(group_order, start=1):
y = participant_avg.loc[participant_avg['Group'] == group, 'Happiness'].values
x = np.random.normal(i, 0.06, size=len(y))
plt.scatter(x, y, color='black', alpha=0.45, s=22)
plt.title('Average Happiness per Participant')
plt.xlabel('Study group')
plt.ylabel('Participant mean happiness')
plt.ylim(0, 10)
finish_plot('07_participant_average_happiness.png')
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

189
dot_config/private_Code/User/History/7da6e0fb/SA9R.py Normal file
View file

@ -0,0 +1,189 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness):')
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(df.loc[mask, habit].astype(int), df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(x='Habits_Count', y='Happiness', data=df, palette='viridis')
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(x='Habits_Count', y='Happiness', data=df, inner=None, palette='muted')
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=participant_avg.index.astype(str), y=participant_avg.values, palette='coolwarm')
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect size example: compare 0 vs 3
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

231
dot_config/private_Code/User/History/7da6e0fb/bwYb.py Normal file
View file

@ -0,0 +1,231 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(data=df, x='Habits_Count', y='Happiness', hue='Habits_Count', palette='viridis', dodge=False)
plt.legend([], [], frameon=False)
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(data=df, x='Habits_Count', y='Happiness', hue='Habits_Count', inner=None, palette='muted', dodge=False)
plt.legend([], [], frameon=False)
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=range(len(participant_avg)), y=participant_avg.values, hue=range(len(participant_avg)), palette='coolwarm', dodge=False)
plt.legend([], [], frameon=False)
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(range(len(participant_avg)), participant_avg.index.astype(str), rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
if 'Group' in df.columns:
plt.figure(figsize=(7, 5))
sns.barplot(data=df, x='Group', y='Happiness', hue='Group', estimator='mean', errorbar='sd', palette='Set2', dodge=False)
plt.legend([], [], frameon=False)
plt.title('Mean Happiness by Group')
plt.ylabel('Average happiness')
f_group = outdir / 'happiness_by_group.png'
plt.tight_layout()
plt.savefig(f_group)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
if 'Group' in df.columns:
sns.scatterplot(data=df, x='Habits_Count', y='Happiness', hue='Group', alpha=0.35)
else:
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

270
dot_config/private_Code/User/History/7da6e0fb/enQE.py Normal file
View file

@ -0,0 +1,270 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_theme(style='whitegrid', context='talk')
def finish_plot(filename):
plt.tight_layout()
plt.savefig(outdir / filename, dpi=200, bbox_inches='tight')
if show_plots:
plt.show()
plt.close()
# 1) Mean happiness by group with error bars
if 'Group' in df.columns:
summary = df.groupby('Group')['Happiness'].agg(['mean', 'std', 'count']).reindex(['Control', 'Intervention'])
ci95 = 1.96 * (summary['std'] / np.sqrt(summary['count']))
plt.figure(figsize=(8, 6))
xpos = np.arange(len(summary))
plt.bar(xpos, summary['mean'].values, color=['#7A7A7A', '#2A9D8F'], yerr=ci95.values, capsize=6)
plt.xticks(xpos, summary.index)
plt.title('Average Happiness by Group')
plt.xlabel('Study group')
plt.ylabel('Mean happiness score')
plt.ylim(0, 10)
finish_plot('01_mean_happiness_by_group.png')
# 2) Distribution of happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(9, 6))
order = ['Control', 'Intervention']
grouped = [df.loc[df['Group'] == group, 'Happiness'].values for group in order]
plt.boxplot(grouped, tick_labels=order, patch_artist=True,
boxprops=dict(facecolor='#C9D1D9', color='#4C4C4C'),
medianprops=dict(color='#2A9D8F', linewidth=2),
whiskerprops=dict(color='#4C4C4C'), capprops=dict(color='#4C4C4C'))
for i, group in enumerate(order, start=1):
y = df.loc[df['Group'] == group, 'Happiness'].values
x = np.random.normal(i, 0.06, size=len(y))
plt.scatter(x, y, color='black', alpha=0.15, s=10)
plt.title('Happiness Distribution by Group')
plt.xlabel('Study group')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('02_happiness_distribution_by_group.png')
# 3) Daily happiness trend by group
if 'Group' in df.columns and 'Day' in df.columns:
daily = df.groupby(['Group', 'Day'], as_index=False)['Happiness'].mean()
plt.figure(figsize=(10, 6))
sns.lineplot(data=daily, x='Day', y='Happiness', hue='Group', hue_order=['Control', 'Intervention'], marker='o')
plt.title('Mean Daily Happiness Across the Study')
plt.xlabel('Day of study')
plt.ylabel('Average happiness')
plt.ylim(0, 10)
plt.xticks(range(1, 31, 2))
finish_plot('03_daily_happiness_trend.png')
# 4) Happiness by number of habits in intervention group only
intervention_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
plt.figure(figsize=(9, 6))
sns.boxplot(data=intervention_df, x='Habits_Count', y='Happiness', color='#4C72B0')
sns.stripplot(data=intervention_df, x='Habits_Count', y='Happiness', color='black', alpha=0.20, jitter=0.18, size=2)
plt.title('Intervention Group: Happiness by Number of Habits Completed')
plt.xlabel('Habits completed that day')
plt.ylabel('Happiness score')
plt.ylim(0, 10)
finish_plot('04_happiness_by_habits_intervention.png')
# 5) Mean happiness by habits count in intervention group
habits_mean = intervention_df.groupby('Habits_Count', as_index=False)['Happiness'].mean()
plt.figure(figsize=(8, 6))
sns.lineplot(data=habits_mean, x='Habits_Count', y='Happiness', marker='o', color='#1F77B4')
plt.title('Intervention Group: Mean Happiness vs Habits Completed')
plt.xlabel('Number of habits completed')
plt.ylabel('Mean happiness')
plt.xticks([0, 1, 2, 3])
plt.ylim(0, 10)
finish_plot('05_mean_happiness_by_habits.png')
# 6) Habit adherence rates in the intervention group
habit_cols = ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']
adherence_rates = intervention_df[habit_cols].mean().sort_values(ascending=False).reset_index()
adherence_rates.columns = ['Habit', 'Rate']
adherence_rates['Habit'] = adherence_rates['Habit'].str.replace('_Adherence', '', regex=False)
plt.figure(figsize=(9, 6))
sns.barplot(data=adherence_rates, x='Habit', y='Rate', color='#E76F51')
plt.title('Intervention Group: Habit Completion Rate')
plt.xlabel('Habit')
plt.ylabel('Proportion completed')
plt.ylim(0, 1)
plt.gca().yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1.0))
finish_plot('06_habit_completion_rate.png')
# 7) Participant average happiness by group
if 'Group' in df.columns:
plt.figure(figsize=(12, 6))
participant_avg = df.groupby(['Group', 'Participant_ID'], as_index=False)['Happiness'].mean()
group_order = ['Control', 'Intervention']
grouped_avgs = [participant_avg.loc[participant_avg['Group'] == group, 'Happiness'].values for group in group_order]
plt.boxplot(grouped_avgs, tick_labels=group_order, patch_artist=True,
boxprops=dict(facecolor='#D6D6D6', color='#4C4C4C'),
medianprops=dict(color='#2A9D8F', linewidth=2),
whiskerprops=dict(color='#4C4C4C'), capprops=dict(color='#4C4C4C'))
for i, group in enumerate(group_order, start=1):
y = participant_avg.loc[participant_avg['Group'] == group, 'Happiness'].values
x = np.random.normal(i, 0.06, size=len(y))
plt.scatter(x, y, color='black', alpha=0.45, s=22)
plt.title('Average Happiness per Participant')
plt.xlabel('Study group')
plt.ylabel('Participant mean happiness')
plt.ylim(0, 10)
finish_plot('07_participant_average_happiness.png')
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

1
dot_config/private_Code/User/History/7da6e0fb/entries.json Normal file
View file

@ -0,0 +1 @@
{"version":1,"resource":"file:///home/breadway/Documents/Year%2010/Year%2010/Psychology/Data%20Analysis.py","entries":[{"id":"SA9R.py","source":"Chat Edit: 'improve on this analysis script'","timestamp":1774345116327},{"id":"ycv3.py","source":"Chat Edit: 'improve data gen.py to add a second dataset as a control. for context, the study tracks the affects of being organised on how happy participants feel. there needs to be a control group that is only recording their happiness daily. the main group will try to record their happiness, will add all events to their calendar, be on time to every event, and clean their bedroom everyday. they report if they do any of these in the study data as a yes or no. the control group will not do any of these.'","timestamp":1774345356264},{"id":"bwYb.py","source":"Chat Edit: 'improve data gen.py to add a second dataset as a control. for context, the study tracks the affects of being organised on how happy participants feel. there needs to be a control group that is only recording their happiness daily. the main group will try to record their happiness, will add all events to their calendar, be on time to every event, and clean their bedroom everyday. they report if they do any of these in the study data as a yes or no. the control group will not do any of these.'","timestamp":1774345411358},{"id":"Gx76.py","source":"Chat Edit: 'improve data gen.py to add a second dataset as a control. for context, the study tracks the affects of being organised on how happy participants feel. there needs to be a control group that is only recording their happiness daily. the main group will try to record their happiness, will add all events to their calendar, be on time to every event, and clean their bedroom everyday. they report if they do any of these in the study data as a yes or no. the control group will not do any of these.'","timestamp":1774345436946},{"id":"FOyN.py","source":"Chat Edit: 'improve data gen.py to add a second dataset as a control. for context, the study tracks the affects of being organised on how happy participants feel. there needs to be a control group that is only recording their happiness daily. the main group will try to record their happiness, will add all events to their calendar, be on time to every event, and clean their bedroom everyday. they report if they do any of these in the study data as a yes or no. the control group will not do any of these.'","timestamp":1774345501736},{"id":"MtI5.py","source":"Chat Edit: 'make the graphs better suited to the study, easier to read, and more graphs.'","timestamp":1774346145201},{"id":"Ldgu.py","source":"Chat Edit: 'make the graphs better suited to the study, easier to read, and more graphs.'","timestamp":1774346200970},{"id":"NtsI.py","source":"Chat Edit: 'make the graphs better suited to the study, easier to read, and more graphs.'","timestamp":1774346222014},{"id":"enQE.py","source":"Chat Edit: 'make the graphs better suited to the study, easier to read, and more graphs.'","timestamp":1774346258056},{"id":"yfjL.py","timestamp":1774346751804},{"id":"9KVj.py","source":"Chat Edit: 'ensure the graphs being used are appropriate for the study'","timestamp":1774346803522}]}

227
dot_config/private_Code/User/History/7da6e0fb/ycv3.py Normal file
View file

@ -0,0 +1,227 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(x='Habits_Count', y='Happiness', data=df, palette='viridis')
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(x='Habits_Count', y='Happiness', data=df, inner=None, palette='muted')
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=participant_avg.index.astype(str), y=participant_avg.values, palette='coolwarm')
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
if 'Group' in df.columns:
plt.figure(figsize=(7, 5))
sns.barplot(data=df, x='Group', y='Happiness', estimator='mean', errorbar='sd', palette='Set2')
plt.title('Mean Happiness by Group')
plt.ylabel('Average happiness')
f_group = outdir / 'happiness_by_group.png'
plt.tight_layout()
plt.savefig(f_group)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
if 'Group' in df.columns:
sns.scatterplot(data=df, x='Habits_Count', y='Happiness', hue='Group', alpha=0.35)
else:
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)

227
dot_config/private_Code/User/History/7da6e0fb/yfjL.py Normal file
View file

@ -0,0 +1,227 @@
import argparse
import os
from pathlib import Path
import logging
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
import statsmodels.formula.api as smf
logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
def load_data(path):
df = pd.read_csv(path)
logging.info("Loaded %d rows from %s", len(df), path)
return df
def prepare_data(df):
# Ensure required columns exist
required = {'Participant_ID', 'Happiness', 'Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence'}
missing = required - set(df.columns)
if missing:
raise KeyError(f"Missing required columns: {missing}")
if 'Group' not in df.columns:
df['Group'] = 'Intervention'
df['Group'] = df['Group'].astype(str).str.strip().str.title()
# Normalize adherence to boolean (Yes/No or True/False)
for col in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
df[col] = df[col].astype(str).str.strip().str.lower().map({'yes': True, 'no': False, 'true': True, 'false': False})
# Count habits per row
df['Habits_Count'] = (
df[['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']].fillna(False).astype(int).sum(axis=1)
)
# Coerce Happiness to numeric and drop rows without Happiness
df['Happiness'] = pd.to_numeric(df['Happiness'], errors='coerce')
before = len(df)
df = df.dropna(subset=['Happiness'])
logging.info('Dropped %d rows without numeric Happiness', before - len(df))
return df
def descriptive_stats(df):
print('Dataset shape:', df.shape)
print('\nOverall summary:')
print(df['Happiness'].describe())
if 'Group' in df.columns:
print('\nRows by group:')
print(df['Group'].value_counts())
print('\nAverage happiness by group:')
print(df.groupby('Group')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nAverage happiness by number of habits completed:')
print(df.groupby('Habits_Count')['Happiness'].agg(['mean', 'count', 'std']).round(3))
print('\nMedian happiness by habits:')
print(df.groupby('Habits_Count')['Happiness'].median())
# Correlations
print('\nPearson correlation between Habits_Count and Happiness:')
print(df[['Habits_Count', 'Happiness']].corr().round(3))
print('\nPoint-biserial correlation (each habit vs happiness, intervention group only):')
habit_df = df[df['Group'] == 'Intervention'] if 'Group' in df.columns else df
for habit in ['Calendar_Adherence', 'Cleanliness_Adherence', 'Punctuality_Adherence']:
mask = ~habit_df[habit].isna()
if mask.sum() == 0:
print(f'{habit:22} (no data)')
continue
r, p = stats.pointbiserialr(habit_df.loc[mask, habit].astype(int), habit_df.loc[mask, 'Happiness'])
print(f"{habit:22} r = {r:.3f} p = {p:.4f}")
def cohen_d(x, y):
# Cohen's d for two independent samples
nx, ny = len(x), len(y)
dof = nx + ny - 2
pooled_sd = np.sqrt(((nx - 1) * x.std(ddof=1) ** 2 + (ny - 1) * y.std(ddof=1) ** 2) / dof)
return (x.mean() - y.mean()) / pooled_sd
def run_ols(df):
if 'Group' in df.columns:
model = smf.ols('Happiness ~ Habits_Count + C(Group)', data=df).fit()
print('\nOLS regression: Happiness ~ Habits_Count + Group')
else:
X = sm.add_constant(df['Habits_Count'])
y = df['Happiness']
model = sm.OLS(y, X).fit()
print('\nSimple OLS regression: Happiness ~ Habits_Count')
print(model.summary())
return model
def run_mixedlm(df):
# Random intercept for Participant_ID
try:
md = smf.mixedlm('Happiness ~ Habits_Count', data=df, groups=df['Participant_ID'])
mdf = md.fit(reml=False)
print('\nMixed-effects model (random intercept by Participant_ID):')
print(mdf.summary())
return mdf
except Exception as e:
logging.warning('MixedLM failed: %s', e)
return None
def make_plots(df, outdir, show_plots=False):
outdir = Path(outdir)
outdir.mkdir(parents=True, exist_ok=True)
sns.set_style('whitegrid')
# Boxplot by Habits_Count
plt.figure(figsize=(9, 6))
sns.boxplot(data=df, x='Habits_Count', y='Happiness', color='#4C72B0')
plt.title('Daily Happiness by Number of Habits Completed')
plt.xlabel('Number of habits followed (0–3)')
plt.ylabel('Happiness (1–10)')
f1 = outdir / 'happiness_by_habits_box.png'
plt.tight_layout()
plt.savefig(f1)
if show_plots:
plt.show()
plt.close()
# Violin / jitter + regression
plt.figure(figsize=(9, 6))
sns.violinplot(data=df, x='Habits_Count', y='Happiness', inner=None, color='#55A868')
sns.stripplot(x='Habits_Count', y='Happiness', data=df, color='k', alpha=0.3, jitter=0.15)
plt.title('Happiness distribution by Habits Completed')
f2 = outdir / 'happiness_by_habits_violin.png'
plt.tight_layout()
plt.savefig(f2)
if show_plots:
plt.show()
plt.close()
# Participant average bar
participant_avg = df.groupby('Participant_ID')['Happiness'].mean().sort_values()
plt.figure(figsize=(12, 5))
sns.barplot(x=range(len(participant_avg)), y=participant_avg.values, color='#C44E52')
plt.axhline(df['Happiness'].mean(), color='black', linestyle='--', alpha=0.6)
plt.xticks(range(len(participant_avg)), participant_avg.index, rotation=45)
plt.title('Average Happiness per Participant (sorted)')
f3 = outdir / 'participant_avg_happiness.png'
plt.tight_layout()
plt.savefig(f3)
if show_plots:
plt.show()
plt.close()
if 'Group' in df.columns:
plt.figure(figsize=(7, 5))
sns.barplot(data=df, x='Group', y='Happiness', estimator='mean', errorbar='sd', color='#8172B2')
plt.title('Mean Happiness by Group')
plt.ylabel('Average happiness')
f_group = outdir / 'happiness_by_group.png'
plt.tight_layout()
plt.savefig(f_group)
if show_plots:
plt.show()
plt.close()
# Scatter with linear fit
plt.figure(figsize=(9, 6))
if 'Group' in df.columns:
sns.scatterplot(data=df, x='Habits_Count', y='Happiness', hue='Group', alpha=0.35)
else:
sns.regplot(x='Habits_Count', y='Happiness', data=df, x_jitter=0.18, scatter_kws={'alpha': 0.4})
plt.title('Happiness vs Number of Habits Completed (with linear fit)')
f4 = outdir / 'happiness_vs_habits_regression.png'
plt.tight_layout()
plt.savefig(f4)
if show_plots:
plt.show()
plt.close()
logging.info('Saved plots to %s', outdir)
def main(args):
df = load_data(args.data)
df = prepare_data(df)
descriptive_stats(df)
# Effect sizes
group0 = df[df['Habits_Count'] == 0]['Happiness']
group3 = df[df['Habits_Count'] == 3]['Happiness']
if len(group0) > 1 and len(group3) > 1:
d = cohen_d(group3, group0)
print(f"\nCohen's d (3 habits vs 0 habits) = {d:.3f}")
if 'Group' in df.columns:
control = df[df['Group'] == 'Control']['Happiness']
intervention = df[df['Group'] == 'Intervention']['Happiness']
if len(control) > 1 and len(intervention) > 1:
d_group = cohen_d(intervention, control)
print(f"Cohen's d (Intervention vs Control happiness) = {d_group:.3f}")
# Models
run_ols(df)
run_mixedlm(df)
# Plots
make_plots(df, args.outdir, show_plots=args.show)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Improved data analysis for organization_happiness_study_data.csv')
parser.add_argument('--data', type=str, default='organization_happiness_study_data.csv', help='CSV data path')
parser.add_argument('--outdir', type=str, default='plots', help='Directory to save plots')
parser.add_argument('--show', action='store_true', help='Show plots interactively')
args = parser.parse_args()
main(args)