How does COVID-19 impact the job market in the Netherlands?¶

pip install -q -r requirements.txt

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
import seaborn as sns
import ipywidgets as widgets

raw_cov_df = pd.read_csv('owid-covid-data.csv')

raw_cov_df.head()

cov_df_nl = raw_cov_df[raw_cov_df['location'] == 'Netherlands']

cov_df_nl.info()

cov_df_nl.describe()

cov_df = cov_df_nl[['date', 'total_cases', 'new_cases', 'total_deaths',
                    'new_deaths', 'total_cases_per_million', 'new_cases_per_million',
                    'total_deaths_per_million', 'new_deaths_per_million',
                    'hosp_patients', 'hosp_patients_per_million']]

cov_df.columns

# Adding 'datetime' column that contains the YYYY-MM for each day
cov_df['datetime'] = pd.to_datetime(cov_df['date'])
cov_df['datetime'] = cov_df['datetime'].dt.date.apply(lambda x: x.strftime('%Y-%m'))

# new dataset with monthly data contains: sum of new_cases, sum of new_deaths, average of hosp_patients per day
cov_df_month = cov_df.groupby('datetime').agg({'new_cases' : 'sum',
                                               'new_deaths' : 'sum',
                                               'hosp_patients' : 'mean'}).reset_index()
cov_df_month

sns.barplot(x='datetime', y='new_cases', data=cov_df_month, color='b', ci=False)
plt.xticks(rotation=90)
plt.title('New COVID cases per month in the Netherlands')
plt.xlabel('Date')
plt.ylabel('New COVID cases')
plt.show()

raw_vac_df = pd.read_csv('84287NED_2021-03-02T12_52_35.csv', sep=";")

raw_vac_df

raw_vac_df.info()

vac_df = raw_vac_df.drop(columns=['BedrijfstakkenBranchesSBI2008_code', 'Perioden_title', 'Unit', 'Measure'])

vac_df.head()

vac_df['datetime'] = vac_df['Perioden_code'].replace('MM', '-', regex=True)
vac_df = vac_df.drop(columns=['Perioden_code'])

cov_vac = cov_df_month.merge(vac_df, on='datetime', how='right')

# Renaming the columns so they're easier to use
cov_vac = cov_vac.rename(columns={'BedrijfstakkenBranchesSBI2008_title' : 'job_industry',
                                  'Value' : 'joboffer_indicator'})

cov_vac.head()

cov_vac = cov_vac.fillna(0)

# Checking if there's any null-values

cov_vac.info()

# Let's see what the df looks like before we start analyzing it
def show_df_rows(Rows):
    return cov_vac.iloc[Rows[0]:Rows[1]]

widgets.interact(show_df_rows, Rows=widgets.IntRangeSlider(value = [0,100],
                                                           min = 0,
                                                           max = len(cov_vac)));

cov_vac_2020 = cov_vac[cov_vac['datetime'].astype('datetime64[ns]') >= pd.to_datetime('2020-03-01')]
cov_vac_2020.corr()

jobplot = sns.lineplot(x='datetime', 
             y='joboffer_indicator',
             hue='job_industry',
             data=cov_vac)

# Adding title and labels
plt.xlabel("Date", size=12)
plt.ylabel("Job-offer indicator", size=12)
plt.title("Job-offer indicator per job industry (2010-2021)", size=20)
plt.xticks(rotation=90)

for ind, label in enumerate(jobplot.get_xticklabels()):
    if ind % 10 == 0:  # every 10th label is kept
        label.set_visible(True)
    else:
        label.set_visible(False)

# Making the graph bigger
fig = plt.gcf()
fig.set_size_inches(15, 8)

plt.show()

# Turn the dates (currently strings) into datetime objects, so we can filter them
cov_vac['datetime'] = pd.to_datetime(cov_vac['datetime'], format='%Y-%m')

cov_vac.head()

# Checkboxes for zooming in/out
checkbox1 = widgets.Checkbox(value = False,
                             description = 'Zoom in',
                             disabled = False)


checkbox2 = widgets.Checkbox(value = False,
                             description = 'Zoom out',
                             disabled = False)


def change_data(val):
    if val == True:
        data = cov_vac[cov_vac['datetime'] > pd.to_datetime('2019-11-01')]
    else:
        data = cov_vac
    
    covplot = sns.lineplot(x='datetime', 
                 y='new_cases',
                 data=data)

    # Adding title and labels
    plt.xlabel("Date", size=12)
    plt.ylabel("New corona cases", size=12)
    plt.title("New corona cases per month", size=20)
    plt.xticks(rotation=90)

    # Making the graph bigger
    fig = plt.gcf()
    fig.set_size_inches(15, 8)
    plt.show()


# Bind checkboxes to change_data function and disable one when the other is checked
out = widgets.interactive_output(change_data, {'val':checkbox1})

widgets.jslink((checkbox2, 'disabled'), (checkbox1, 'value'));
widgets.jslink((checkbox1, 'disabled'), (checkbox2, 'value'));
widgets.VBox([widgets.HBox([checkbox1, checkbox2]), out])

def draw_plot(selection_y, selection_hue):
    # Setting the selected variables
    y = cov_vac[cov_vac["job_industry"] == selection_y]['joboffer_indicator']
    hue = selection_hue;

    # Plotting the joboffer indicator per job field
    ax = sns.lineplot(x = 'datetime', 
                      y = y,                      # <--- Selected y
                      hue = hue,                  # <--- Selected hue
                      data = cov_vac)
    
    if selection_hue:                             # <--- Only show legend if there's multiple lines
        ax.legend(loc='upper left')
    
    ax.set_ylabel('Job-offer indicator')
    ax.set_xlabel('Year')

    # Plotting the new_cases line
    ax2 = ax.twinx()
    cov_vac.plot(x = "datetime",
                 y = "new_cases",
                 ax = ax2,
                 color = "0")
    ax2.legend(loc = 'lower left')
    ax2.set_ylabel('New COVID cases per month')

    # Resizing the plot
    fig = plt.gcf()
    fig.set_size_inches(14, 6)
    
    # Add titles and show plot
    plt.title("COVID cases vs. job-offer indicator in the Netherlands, per month", size = 14)
    plt.show()

# Dropdown1: if "View all industries is selected, disable the "Industry" dropdown
def toggle_dropdown2(val):
    dropdown2.disabled = val
    dropdown2.value = None

dropdown1 = widgets.Dropdown(
                options = [('All industries', True),
                           ('Specific industry', False)],
                description = 'View: ')



# Dropdown 2: chooses a specific industry to plot (y)
def select_y(Industry):
    if not dropdown2.disabled and not dropdown2.value == None:    # Plots selected industry
        draw_plot(Industry, None)
    else:                                                         # Plots all industries if disabled/empty
        draw_plot(cov_vac["job_industry"], 'job_industry')

dropdown2 = widgets.Dropdown(
                value = None,
                options = [('F Construction industry', 'F Bouwnijverheid'),
                           ('C Manifacturing industry', 'C Industrie'),
                           ('G-N Commercial services', 'G-N Commerciële dienstverlening'),
                           ('A-U All economic activities', 'A-U Alle economische activiteiten')],
                description = 'Industry: ',
                disabled=True)



# Link the dropdowns to their corresponding functions
widgets.interact(toggle_dropdown2, val=dropdown1);
widgets.interact(select_y, Industry=dropdown2);