def test_lorenz_curve():
"""
Tests `lorenz` function, which calculates the lorenz curve
An income distribution where everyone has almost the same wealth should
be similar to a straight line
An income distribution where one person has almost the wealth should
be flat and then shoot straight up when it approaches one
"""
n = 3000
# Almost Equal distribution
y = np.repeat(1, n) + np.random.normal(scale=0.0001, size=n)
cum_people, cum_income = lorenz_curve(y)
assert_allclose(cum_people, cum_income, rtol=1e-03)
# Very uneven distribution
y = np.repeat(0.001, n)
y[4] = 100000
pop_cum, income_cum = lorenz_curve(y)
expected_income_cum = np.repeat(0., n + 1)
expected_income_cum[-1] = 1.
assert_allclose(expected_income_cum, income_cum, atol=1e-4)
def test_lorenz_curve():
"""
Tests `lorenz` function, which calculates the lorenz curve
An income distribution where everyone has almost the same wealth should
be similar to a straight line
An income distribution where one person has almost the wealth should
be flat and then shoot straight up when it approaches one
"""
n = 3000
# Almost Equal distribution
y = np.repeat(1, n) + np.random.normal(scale=0.0001, size=n)
cum_people, cum_income = lorenz_curve(y)
assert_allclose(cum_people, cum_income, rtol=1e-03)
# Very uneven distribution
y = np.repeat(0.001, n)
y[4] = 100000
pop_cum, income_cum = lorenz_curve(y)
expected_income_cum = np.repeat(0., n + 1)
expected_income_cum[-1] = 1.
assert_allclose(expected_income_cum, income_cum, atol=1e-4)
def update_tabs(n_clicks, reference_lines, selected_sectors, shock, empresa,
formalidad, contrato):
# descriptive statistics
mediana_choque = 'No choque'
texto_mediana = 'Mediana choque: {}'.format(mediana_choque)
pobreza_choque = 'No choque'
texto_pobreza = u'Índice de pobreza choque: {}'.format(pobreza_choque)
# get context
ctx = dash.callback_context
if not ctx.triggered:
return fig_hist, texto_mediana, fig_lorenz, texto_pobreza
else:
action_id = ctx.triggered[0]['prop_id'].split('.')[0]
if action_id == 'apply-button':
# ----------------------------
# 1. Datos
print(datetime.datetime.now())
print('Updating data...')
# ----------------------------
if formalidad is None:
formalidad = []
if contrato is None:
contrato = []
if selected_sectors is None:
selected_sectors = []
# reestablezco la base
df_shock = df.copy()
# definicion de hogares en riesgo
df_shock.loc[(((df_shock['sector'].isin(selected_sectors)) &
(df_shock['tipo_empresa'] == empresa)) &
((df_shock['informales'].isin(formalidad)) |
(df_shock['cuenta_propia'].isin(contrato)))),
'riesgo'] = 1
df_shock.riesgo = df_shock.riesgo.fillna(value=0)
df_shock = update_income(df_shock, shock)
# ----------------------------
# 2. Histograma y mediana
print('Updating Histogram...')
# ----------------------------
# clean histogram
fig_hist.data = []
# compute kernel
kernel_shock = gaussian_kde(df_shock.ING_pc_choque_arriendo,
weights=df_shock.fac_exp_ind_12m)
# update median
mediana_choque = weighted_median(df_shock, 'ING_pc_choque_arriendo',
'fac_exp_ind_12m')
texto_mediana = 'Mediana choque: {:,.0f} COP'.format(mediana_choque)
# modified distribution
fig_hist.add_trace(
go.Scatter(x=xs,
y=kernel_shock(xs),
name=u'Distribución Choque',
line_color=naranja,
fill='tozeroy',
fillcolor='rgba(237,177,131,0.5)',
mode='lines'))
# Original distribution
fig_hist.add_trace(
go.Scatter(x=xs,
y=dist_original,
mode='lines',
name=u'Distribución Original',
line=dict(color=black)))
# ----------------------------
# 3. Lorenz
print('Updating Lorenz...')
# ----------------------------
# clean figure
fig_lorenz.data = []
fig_lorenz.add_trace(
go.Scatter(x=[0, 1],
y=[0, 1],
mode='lines',
name=u'Igualdad total',
line=dict(color='grey', dash="dashdot")))
# calculate new values
f_vals_shock, l_vals_shock = qe.lorenz_curve(
df_shock.ING_pc_choque_arriendo.to_numpy())
# sample to plot
ids = list(range(0, len(f_vals)))
sample_ids = random.sample(ids, 10000)
fig_lorenz.add_trace(
go.Scatter(x=f_vals_shock[sample_ids],
y=l_vals_shock[sample_ids],
mode='lines',
name=u'Distribución Choque',
line_color=naranja))
fig_lorenz.add_trace(
go.Scatter(x=f_vals[sample_ids],
y=l_vals[sample_ids],
mode='lines',
name=u'Distribución Original',
line_color=black))
# ----------------------------
# 4. Poverty
print('Updating Poverty Measures... \n')
print('-------------------------------------')
# ----------------------------
pobreza_choque = calculo_pobreza(df_shock, 'ING_pc_choque_arriendo')
texto_pobreza = u'Índice de pobreza choque: {:.2f}%'.format(
pobreza_choque)
elif action_id == 'reference-lines':
lines, names = generate_reference_lines(reference_lines, dist_original)
fig_hist.update_layout(shapes=lines, annotations=names)
else:
raise PreventUpdate
return fig_hist, texto_mediana, fig_lorenz, texto_pobreza
mode='lines',
name=u'Distribución Original',
line=dict(color=black)))
# summary statistics
median_original = weighted_median(df, 'ING_pc_bl_def_arriendo',
'fac_exp_ind_12m')
# Lorenz curve and GINI (https://python.quantecon.org/wealth_dynamics.html)
# TODO: weighted version of these calculations
# start = time.time()
# gini_original = qe.gini_coefficient(df.ING_pc_bl_def_arriendo.to_numpy())
# print('Gini calculated in {} minutes'.format((time.time()-start)/60))
f_vals, l_vals = qe.lorenz_curve(df.ING_pc_bl_def_arriendo.to_numpy())
fig_lorenz = go.Figure(
layout=go.Layout(title=go.layout.Title(text=u"Curva de Lorenz"),
xaxis=go.layout.XAxis(
title="Porcentaje acumulado de personas"),
yaxis=go.layout.YAxis(
title="Porcentaje acumulado del ingreso"),
plot_bgcolor='white',
paper_bgcolor='white',
font_color='grey',
showlegend=True))
# sample to plot
ids = list(range(0, len(f_vals)))
sample_ids = random.sample(ids, 10000)