def __init__(self, address, db):
for key in ['Year', 'Month', 'Arrest', 'Latitude', 'Longitude']:
if key not in db.columns:
raise ValueError('Database does not contain mandatory "{}" column.'.format(key))
if not isinstance(address, Address):
raise TypeError('Receive address is not of type addressClass.Address')
self.address = address
district = address.district
district_db = self._filter_db_by_district(district,db)
self.district = district
#Setting attributes to total district info
self.dist_crime_density = iu.get_density(polygon = du.get_polygon(district), ammount = len(district_db))
self.dist_police_effectiveness = iu.effectiveness_police(data = district_db)
self.dist_police_effectiveness_density = iu.effectiveness_sq_mile(polygon = du.get_polygon(district), data = district_db)
#Setting attributes by month/year from the district
self.dist_crime_density_month = self._generate_db_month_district_indicator(district_db, 'density')
self.dist_police_effectiveness_month = self._generate_db_month_district_indicator(district_db,'effect')
self.dist_police_effectiveness_density_month = self._generate_db_month_district_indicator(district_db, 'effectsq')
circle_data = self._get_data_crime_circle(db)
#Setting attributes to circle, total info
self.circ_crime_density = iu.get_density(polygon = self._get_circle_boundaries(), ammount = len(circle_data))
self.circ_police_effectiveness = iu.effectiveness_police(data = circle_data)
self.circ_police_effectiveness_density = iu.effectiveness_sq_mile(polygon = self._get_circle_boundaries(), data = circle_data)
#Setting attributes to circle, by month/year
self.circ_crime_density_month = self._generate_db_month_district_indicator(circle_data, 'density')
self.circ_police_effectiveness_month = self._generate_db_month_district_indicator(circle_data,'effect')
self.circ_police_effectiveness_density_month = self._generate_db_month_district_indicator(circle_data, 'effectsq')
def crime_density_by_district(self):
"""
Computes the indicator of number of crimes per square mile by district in the whole Chicago area
Its output is a dictionary with each value, where key is the number of district
"""
crime_per_milesq = {}
for district in self.districts_contained:
data_district = self[self['District'] == district]
try:
crimes_per_district = iu.get_density(polygon=du.get_polygon(district), ammount=len(data_district))
except iu.ZeroAreaPolygon as errmessage:
crime_per_milesq[district] = np.nan
else:
crime_per_milesq[district] = crimes_per_district
return crime_per_milesq
def test_get_density(self): self.assertTrue(iu.get_density(self.boundaries, len(self.data)))
def _generate_db_summarized_for_district(self, db):
"""
This functions returns a dataframe of the indicators per month/year.
It filters the data in year and then in month, so that it can compute the indicators in each subset (month and year).
As a note, it uses the following pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')
in order to create the index as a date type, making it easier to plot later.
:param db:
"""
Years = db.Year.unique()
data_ind = pd.DataFrame(columns=('density', 'effectiveness', 'effect_by_sqm'))
for year in Years:
data_year = db[db['Year'] == year]
for month in range(1,13):
data_district_month = data_year[data_year.Month == month]
if len(data_district_month) == 0:
data_ind.loc[ pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] =[np.nan, np.nan, np.nan]
else:
data_ind.loc[pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] = [iu.get_density(polygon=du.get_polygon(district_number=self.district), ammount= len(data_district_month)),
iu.effectiveness_police(data=data_district_month),
iu.effectiveness_sq_mile(polygon = du.get_polygon(self.district), data =data_district_month)]
return data_ind
def _generate_db_month_district(self, district=0):
"""
Filters the DB according to the district and generates a dictionary with the number of
crimes by month and year, for each indicator.
If district is set to zero, computes the total of all Chicago.
As a note, it uses the following pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')
in order to create the index as a date type, making it easier to plot later.
If there is no crime data, it sets the value Nan from numpy. Returns a a dictionary of the number of crimes
:return data_ind
"""
Years = self.Year.unique()
data_ind = pd.DataFrame(columns=('density', 'effectiveness', 'effect_by_sqm'))
#CHicago considers the total information by month/year
if district == 0:
area = 0
for district in self.districts_contained:
area += proj.PolygonProjection(du.get_polygon(district)).calculate_area_in_miles()
for year in Years:
data_district_year = self[self['Year'] == year]
for month in range(1,13):
data_district_month = data_district_year[data_district_year['Month'] == month]
if len(data_district_month) == 0:
data_ind.loc[ pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] =[np.nan, np.nan, np.nan]
else:
data_ind.loc[ pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] = [ len(data_district_month)/ area,
len(data_district_month[data_district_month['Arrest'] == True])*1.0 / len(data_district_month),
(len(data_district_month[data_district_month['Arrest'] == True])*1.0 / len(data_district_month['Arrest']))/area]
#Other case, it computes the indicator of the inputted district
else:
for year in Years:
data_district_year = self[(self['District'] == district) & (self['Year'] == year)]
for month in range(1,13):
data_district_month = data_district_year[data_district_year['Month'] == month]
if len(data_district_month) == 0:
data_ind.loc[ pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] =[np.nan, np.nan, np.nan]
else:
data_ind.loc[ pd.datetime.strptime(str(int(month)).zfill(2)+str(year), '%m%Y')] = [iu.get_density(polygon = du.get_polygon(district), ammount = len(data_district_month)),
iu.effectiveness_police(data_district_month),
iu.effectiveness_sq_mile(polygon = du.get_polygon(district), data =data_district_month)]
return data_ind
