def getLine(geographicValue, target, states, year, month):
startPeriod, endPeriod = utils.parse_dates(year, month)
if geographicValue == 'Department':
tmp = df[(df['depto_establecimiento'].isin(states))
& (df['target'] == target)]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp.groupby(
['interno', 'depto_establecimiento',
'Ingreso_Month']).count().reset_index()
grouped = tmp.groupby(['depto_establecimiento',
'Ingreso_Month']).count().reset_index()
elif geographicValue == 'National':
tmp = df[df['target'] == target]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
grouped = tmp.groupby(
['Ingreso_Month']).count().reset_index() # count unique convict ID
grouped['national'] = "Colombia"
fig = line_Plot(grouped, geographicValue)
for ser in fig['data']:
ser['hovertemplate'] = '%{x}<br>%{y}'
return fig
def getBarsentence(geographicValue, target, states, year, month):
startPeriod, endPeriod = utils.parse_dates(year, month)
tmp = df[df['target'] == target]
if geographicValue == 'Department':
targetgeo = "depto_establecimiento"
tmp = tmp[tmp['depto_establecimiento'].isin(states)]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp[["interno", "sentencia", targetgeo]]
elif geographicValue == 'National':
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp[["interno", "sentencia"]]
tmp.drop_duplicates(subset="interno", keep='first', inplace=True)
tmp = tmp.reset_index(drop=True)
bins = range(0, 13)
labels = range(1, 13, 1)
tmp['sentence_group'] = pd.cut(tmp.sentencia,
bins,
labels=labels,
include_lowest=True)
grouped = tmp.groupby([
"sentence_group"
])["interno"].count().reset_index().sort_values("sentence_group")
fig = barsentence_Plot(grouped, geographicValue)
fig.data[0].hovertemplate = '%{label}<br>%{value}'
return fig
def getBarage(geographicValue, target, states, year, month):
startPeriod, endPeriod = utils.parse_dates(year, month)
tmp = df[df['target'] == target]
if geographicValue == 'Department':
targetgeo = "depto_establecimiento"
tmp = tmp[tmp['depto_establecimiento'].isin(states)]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp[["interno", "edad", "genero", targetgeo]]
elif geographicValue == 'National':
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp[["interno", "edad", "genero"]]
tmp.drop_duplicates(subset="interno", keep='first', inplace=True)
tmp = tmp.reset_index(drop=True)
bins = [18, 25, 35, 45, 55, 65, 100]
labels = ['18-25', '26-35', '36-45', '46-55', '56-65', '65+']
tmp['age_range'] = pd.cut(tmp.edad,
bins,
labels=labels,
include_lowest=True)
# grouped = tmp.groupby(["age_range", "genero", targetgeo])["interno"].count().reset_index().sort_values("age_range")
grouped = tmp.groupby(
["age_range",
"genero"])["interno"].count().reset_index().sort_values("age_range")
fig = barage_Plot(grouped, geographicValue)
fig.data[0].hovertemplate = '%{label}<br>%{value}'
fig.data[1].hovertemplate = '%{label}<br>%{value}'
return fig
def getBlock(geographicValue, target, states, year, month):
startPeriod, endPeriod = utils.parse_dates(year, month)
tmp = df[df['target'] == target]
if geographicValue == 'Department':
tmp = tmp[tmp['depto_establecimiento'].isin(states)]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) & (
tmp['Ingreso_Month'] < endPeriod)] # filter dataset by the daterange
grouped = tmp.groupby([
"delito"
]).size().reset_index(name="count").sort_values(by="count",
ascending=False)
if grouped.shape[0] > 50:
grouped = grouped.iloc[:50]
else:
grouped
fig = block_Plot(grouped, geographicValue)
return fig
def get_map_data(geographicValue, target, year, month):
startPeriod, endPeriod = utils.parse_dates(year, month)
if geographicValue == 'Department':
tmp = df[df['target'] == target]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp = tmp.groupby(['interno', 'depto_establecimiento'
]).count().reset_index() # count unique convict ID
grouped = tmp.groupby(['depto_establecimiento']).count().reset_index()
grouped['normalized_count'] = 100 * grouped['interno'] / grouped[
'interno'].sum()
missing_depto = {
'depto_establecimiento':
["VAUPES", "VICHADA", "GUAVIARE", "GUAINIA"],
'interno': [0, 0, 0, 0],
'normalized_count': [0, 0, 0, 0]
}
add_missing = pd.DataFrame(data=missing_depto)
grouped_final = pd.concat([grouped, add_missing], ignore_index=True)
grouped_final.fillna(0, inplace=True)
figure = map_departamentos(grouped_final)
elif geographicValue == 'National':
tmp = df[df['target'] == target]
tmp = tmp[(tmp['Ingreso_Month'] >= startPeriod) &
(tmp['Ingreso_Month'] <
endPeriod)] # filter dataset by the daterange
tmp[geographicValue] = "Colombia"
tmp = tmp.groupby(['interno', geographicValue
]).count().reset_index() # count unique convict ID
grouped = tmp.groupby([geographicValue]).count().reset_index()
figure = map_national(grouped)
return figure