[Python] How do I rewrite my Python script to avoid AI detection? [closed]

My Python script is flagging as AI-generated in a ChatGPT detector. I want to avoid that. Could someone tweak my Python script to make it seem more human-written and less AI-detectable?

import os
import sys
import pandas as pd
import numpy as np


def load_population_csv(csv_file_path):
"""
Load and tidy a CSV of prefecture populations by year.
"""
raw_df = pd.read_csv(csv_file_path)
raw_df.rename(columns={'Prefecture': 'prefecture_name'}, inplace=True)

records = []
for _, row in raw_df.iterrows():
prefecture = row.prefecture_name
for column in raw_df.columns:
if column == 'prefecture_name':
continue
census_year = int(column)
raw_value = row[column]
records.append({
'prefecture_name': prefecture,
'year': census_year,
'population_raw': raw_value
})

expanded_df = pd.DataFrame(records)

cleaned_populations = []
for raw_val in expanded_df['population_raw']:
text = str(raw_val).replace(',', '').strip()
if text == '–' or not text.isdigit():
cleaned_populations.append(np.nan)
else:
# original data is in thousands
cleaned_populations.append(int(text) * 1000)

expanded_df['population'] = cleaned_populations
expanded_df.dropna(subset=['population'], inplace=True)
expanded_df['population'] = expanded_df['population'].astype(int)

return expanded_df[['prefecture_name', 'year', 'population']]


if __name__ == '__main__':
# Determine data directory
data_dir = os.getenv('PG_DATA_DIR', r'C:\pg_data')
if not os.path.isdir(data_dir):
print('Data directory missing:', data_dir)
sys.exit(1)

# Load historical population data
historical_population_df = load_population_csv(
os.path.join(data_dir, 'prefecture_population_1920_2020.csv')
)

# Load mortality and migration data
mortality_df = pd.read_csv(os.path.join(data_dir, 'Mortality.csv'))
migration_df = pd.read_csv(os.path.join(data_dir, 'Migration.csv'))
mortality_df.rename(columns={'Prefecture': 'prefecture_name'}, inplace=True)
migration_df.rename(columns={'Prefecture': 'prefecture_name'}, inplace=True)

# Identify the most recent year in both datasets
latest_mortality_year = max(int(col) for col in mortality_df.columns if col.isdigit())
latest_migration_year = max(int(col) for col in migration_df.columns if col.isdigit())
if latest_mortality_year != latest_migration_year:
print(f'Years differ: mortality {latest_mortality_year}, migration {latest_migration_year}')
sys.exit(1)
forecast_start_year = latest_mortality_year

# Create lookup dicts for rates
mortality_rate = mortality_df.set_index('prefecture_name')[str(forecast_start_year)].to_dict()
migration_rate = migration_df.set_index('prefecture_name')[str(forecast_start_year)].to_dict()

# Prepare base populations for forecasting
last_hist_year = historical_population_df['year'].max()
future_years = range(last_hist_year + 1, 2041)
base_population = (
historical_population_df
.query('year == @last_hist_year')
.set_index('prefecture_name')['population']
.to_dict()
)

# Forecast future populations
forecast_records = []
for prefecture, initial_pop in base_population.items():
projected_pop = initial_pop
for year in future_years:
annual_rate = (mortality_rate.get(prefecture, 0) + migration_rate.get(prefecture, 0)) / 1000.0
projected_pop = int(projected_pop * (1 + annual_rate))
forecast_records.append({
'prefecture_name': prefecture,
'year': year,
'population': projected_pop
})

forecast_df = pd.DataFrame(forecast_records)

# Combine historical and forecast data with clear columns
hist_df = historical_population_df.rename(columns={'population': 'historical_population'})
hist_df = hist_df[['prefecture_name', 'year', 'historical_population']].assign(population=np.nan)
fore_df = forecast_df[['prefecture_name', 'year', 'population']].assign(historical_population=np.nan)
merged_df = pd.concat([hist_df, fore_df], ignore_index=True)

# Fill final population: historical where available, else forecast
merged_df['population'] = merged_df['historical_population'].combine_first(merged_df['population']).astype(int)

# Extract forecasts for 2021 onward and save
output_df = merged_df.query('year >= 2021')[['prefecture_name', 'year', 'population']]
output_file = os.path.join(data_dir, 'testing_prefecture_forecasts_2021_2040_counts.csv')
output_df.to_csv(output_file, index=False)
print('Done. Saved forecasts to', output_file)

# Print total population per year
total_by_year = output_df.groupby('year')['population'].sum()
print('\nTotals:')
for year, total in total_by_year.items():
print(f'{year}: {total:,}')

Continue reading...