def explore_02_bar_counties_count(df_to_explore):
# Transform the dataset for exploration
find_criteria_total = df_to_explore['criteria_tidy'] == 'TOTAL MARK'
find_year_2019 = df_to_explore['year'] == 2019
choose_rows = find_criteria_total & find_year_2019
output_df = df_to_explore[choose_rows].sort_values(by=['county_l1'])
# Make a plot, and write it to a .png file
output_file_name = 'output/cleaner_marks_df_2014_02_bar_counties_count.png'
output_plot = {
'df_x': 'county_l1',
'df_y': 'mark',
'estimator': np.count_nonzero,
'title': 'Adjudicated towns by counties for 2019',
'x_label': 'County',
'y_label': 'Towns'
}
barplot_df_to_png(output_df, output_file_name, output_plot, (6.6, 1))
def explore_05_bar_categories_marks_median(df_to_explore):
# Transform the dataset for exploration
find_criteria_total = df_to_explore['criteria_tidy'] == 'TOTAL MARK'
find_year_2019 = df_to_explore['year'] == 2019
choose_rows = find_criteria_total & find_year_2019
output_df = df_to_explore[choose_rows].sort_values(by=['category'])
# Make a plot, and write it to a .png file
output_file_name = 'output/cleaner_marks_df_2014_05_bar_categories_marks_median.png'
output_plot = {
'df_x': 'category',
'df_y': 'mark',
'estimator': np.median,
'ylim': (270, 350),
'title': 'Median \'TOTAL MARK\' by categories for 2019',
'x_label': 'Category',
'y_label': 'Median Mark'
}
barplot_df_to_png(output_df, output_file_name, output_plot, (3.2, 1))