This is an embedded juipyter notebook file that I created to make a heatmap of SWE over 2 decades period at Mores Creek Summit, Boise. The data used in this article can be downloaded from USDA.
As usual, the first thing is to import all required packages.
# import modules
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import glob
import os
import matplotlib.pyplot as plt
import seaborn as sns
#Print the current working directory
os.getcwd()
Out[ ]:
# use the glob function of the glob modeule to return a list of all csv files
data_dir = glob.glob('MCS_SNOWTEL/SWE/*.csv')
data_dir
Out[ ]:
#read the csv files into a list of dataframes
dataframes = []
for file in data_dir:
dataframes.append(pd.read_csv(file, header=1,index_col= 'Date', usecols= ['Date', 'WTEQ.I-1 (in) '], na_values = -99.9))
dataframes
Out[ ]:
#concatenate the dataframes into one dataframe and sort based on date index
df = pd.concat(dataframes).sort_index()
df
Out[ ]:
df.columns
Out[ ]:
#display the data frame info
df.info()
#find the min and max of the dataframe
print('The min of values in the dataframe is {} \nThe max is {}'.format(df['WTEQ.I-1 (in) '].min(),df['WTEQ.I-1 (in) '].max()))
# count the number of null values in the dataframe
df['WTEQ.I-1 (in) '].isnull().sum()
Out[ ]:
Since there are only 22 NAN values out of the 8k data, we can drop the null values.
# drop the null values
df = df.dropna()
df['WTEQ.I-1 (in) '].isnull().sum()
Out[ ]:
#Set to datetime format
df.index = pd.to_datetime(df.index)
df
Out[ ]:
# calculate the monthly mean
df_monthly = df.resample('M').mean()
df_monthly
Out[ ]:
#change the unit of the SWE values to centimeter
df_monthly['SWE (cm)'] = df_monthly['WTEQ.I-1 (in) '] * 2.54
df_monthly
Out[ ]:
# Create a column of the month and year
df_monthly['Month'] = df_monthly.index.month_name()
df_monthly['Year'] = df_monthly.index.year
df_monthly
Out[ ]:
#pivot the dataframe to ctabularize the monthly mean
df_monthly_pivot = df_monthly.pivot("Month", "Year", "SWE (cm)") #drop column
df_monthly_pivot
Out[ ]:
#sort by string month column and drop the 1999 column
df_monthly_pivot.index = pd.Categorical(df_monthly_pivot.index,
categories=['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December'],
ordered=True)
df_monthly_pivot.drop(1999, axis=1, inplace=True)
df_monthly_pivot = df_monthly_pivot.sort_index()
df_monthly_pivot
Out[ ]:
# Set font size and font family
plt.rcParams.update({'font.size': 18})
plt.rcParams['font.family'] = 'serif'
plt.rcParams['font.serif'] = ['Times New Roman'] + plt.rcParams['font.serif']
#create a figure and axes elements
fig, ax = plt.subplots(figsize=(13,9), constrained_layout=True)
#create a heatmap of the monthly mean using seaborn
sns.heatmap(df_monthly_pivot, linewidth = .5, cmap = 'YlGnBu', ax=ax)
#set title
ax.set_title('Monthly Mean SWE (cm) at Mores Creek Summit, ID')
plt.show()
#save the figure
fig.savefig('Monthly_Mean_SWE.jpeg', dpi=500)
In [ ]:
