#!/usr/bin/env python
# coding: utf-8

# In[2]:


import xarray as xr
import numpy as np 
import matplotlib.pyplot as plt
import glob
import pandas as pd


# In[31]:

#Define file path to open data

#path1 = str(input('File_path_1: '))
#path2 = str(input('File_path_2: '))

path1 = r'/work/users/hmo/remoclic/Phuong/PHD/BC_2023/Tan/NC/'
path2 = r'/work/users/hmo/remoclic/Phuong/PHD/BC_2023/Tan/NC/'

#Open and sort the list of file in the previous path 
#list_of_files = sorted(glob.glob(path1), key = lambda x: x.split('_')[-1])
#list_of_files_2 = sorted(glob.glob(path2), key = lambda x: x.split('_')[-1])

#list_of_files   = ["Geo_ORIG_CNRM.nc","Geo_ORIG_CSIRO.nc","Geo_ORIG_ECEA.nc","Geo_ORIG_GFDL.nc","Geo_ORIG_HadG.nc","Geo_ORIG_MPI.nc","Geo_ORIG_ENS.nc"]
#list_of_files_2 = ["Geo_QM_CNRM.nc","Geo_QM_CSIRO.nc","Geo_QM_ECEA.nc","Geo_QM_GFDL.nc","Geo_QM_HadG.nc","Geo_QM_MPI.nc","Geo_QM_ENS.nc"]

list_of_files = ["CNRM","CSIRO","ECEA","GFDL","HadG","MPI","ENS"]

print(list_of_files)
#print(list_of_files_2)

Xlab=[]
Del1=[]
Del2=[]
for i in range(0,len(list_of_files)):
    del1=1 + i*3
    del2=2 + i*3
    xlab=i+1
    Del1.append(del1)
    Del2.append(del2)
    Xlab.append(xlab)

list1=[]
list2=[]
for file in list_of_files:
    list1.append(path1+'Geo_ORIG_'+file+'.nc')
    list2.append(path1+'Geo_QM_'+file+'.nc')

# In[18]:

#Write a function to collect "geo" data from the file path, store in a dataset with the columns name is the name of the file
def create_dataframe(file_paths, var):
    # Create an empty dictionary to store the data of geo
    data_dict = {}

    # Iterate over the file paths
    for file_path in file_paths:
        # Open the netcdf dataset with xarray library 
        dataset = xr.open_dataset(file_path)

        # Extract the data of variable
        var_data = dataset[var][0]

        # Get the file name without the directory and extension
        file_name = file_path.split('\\')[-1].split('.')[0]

        # Store the data in the dictionary with the file name as the key
        data_dict[file_name] = var_data.values

    # Create the DataFrame from the dictionary
    df = pd.DataFrame(data_dict)

    return df

#Output data storing the variables needed to plot 
#df = create_dataframe(list_of_files, var = 'geo')
#df1 = create_dataframe(list_of_files_2, var = 'geo')

df  = create_dataframe(list1, var = 'geo')
df1 = create_dataframe(list2, var = 'geo')


# In[28]:


# Create a box plot for each column in the DataFrame
fig, ax = plt.subplots(figsize=(10, 6))

#Set the labels
labels = df.columns

#Plot the boxplot for dataframe
c = "red"
bplot1 = ax.boxplot(df, positions = Del1,
                    notch = True,
                    vert = True,
                    patch_artist = True, 
                   # labels = list_of_files,
                   # labels = Del1,
                   ## labels = Xlab,
                    boxprops=dict(facecolor=c, color=c))

c1 ="blue"
bplot2 = ax.boxplot(df1, positions = Del2,
                    notch = True,
                    vert = True,
                    patch_artist = True, 
                   # labels = list_of_files,
                   ## labels = Xlab,
                    boxprops=dict(facecolor=c1, color=c1))

ax.set_xticklabels(list_of_files)

#Set the title for figure by the last character of columns name
ax.set_title('Box plot of '+ str(df.columns[0]).split('_')[0] + ' data')


# Display the plot
#plt.show()

#Save figure
plt.savefig('test.pdf')