import numpy as np
import [Link] as plt
from distfit import distfit
import pandas as pd
# Load the data from CSV with error handling
try:
df1 = pd.read_csv('D:\\pythonProject1\\venv\\Rain_imd\\IMD_DataSET\\
Sarotry_monthly_tmp_prp.csv')
except FileNotFoundError:
print("The specified file was not found. Please check the path.")
exit()
except [Link]:
print("The file is empty. Please check the file.")
exit()
# Set the columns based on your description
[Link] = ['Month', 'prp', 'tmin', 'tmax', 'flow']
df1['Month'] = pd.to_datetime(df1['Month'], format='%B-%Y') # Convert to datetime
# Initialize the distfit object
df = distfit()
# List of monsoon months (June to September)
monsoon_months = [6, 7, 8, 9]
# Create a list to hold the results for each variable and month
results = []
# List of variables to analyze
variables = ['prp', 'tmin', 'tmax', 'flow']
# Create a plot for each monsoon month and each variable
for month in monsoon_months:
for var in variables:
monthly_data = df1[df1['Month'].[Link] == month][var].to_numpy()
monthly_data = monthly_data[~[Link](monthly_data)] # Remove NaN values
if present
# Check if there is data to fit
if len(monthly_data) > 0:
# Fit the data to a distribution
df.fit_transform(monthly_data)
# Get summary of the fitted distributions
summary = [Link]
best_fit = [Link][0] # Get the best fitting distribution
# Collect results for the month and variable
[Link]({
'Month': df1['Month'].dt.month_name()[month - 1], # Month name
'Variable': var,
'Best Distribution': best_fit['name'],
'Parameters': best_fit['params']
})
# Plot the results
[Link]()
[Link]()
[Link](f"Distribution Fit for {df1['Month'].dt.month_name()[month -
1]} - {var}") # Month and variable name
[Link](f"{var} values")
[Link]("Density")
plt.tight_layout() # Improve layout
# Save the figure
[Link](f"Distribution_Fit_{df1['Month'].dt.month_name()[month -
1]}_{var}.png") # Save figure as PNG
[Link]() # Close the figure to avoid displaying it
else:
print(f"No data available for {df1['Month'].dt.month_name()[month - 1]}
in {var}")
# Create a DataFrame from the results
results_df = [Link](results)
# Print the summary DataFrame
print("\nSummary of Best Fitting Distributions for Monsoon Months:")
print(results_df)
# Export the results to a CSV file
results_df.to_csv('monsoon_distribution_fits_all_variables.csv', index=False)
print("\nResults have been exported to
'monsoon_distribution_fits_all_variables.csv'.")
# Optionally, show all plots (if you wish to see them)
# [Link]()
