def get_school_type_age_ranges(location_data):
"""
Read in the school type and age range data from csv files and format the
data to add to the location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
dict : An dictionary mapping school type to the distinct age range for
each school type.
"""
df = pd.read_csv(
os.path.join(
sp.settings.datadir, location_data.location_name,
f"{location_data.location_name}_school_type_age_ranges.csv"))
arr = sp.convert_df_to_json_array(df,
cols=df.columns,
int_cols=['age_min', 'age_max'])
school_type_age_ranges = []
for si in range(len(arr)):
s = sp.SchoolTypeByAge()
school_type = arr[si][0]
s.school_type = school_type
s.age_range = [arr[si][1], arr[si][2]]
school_type_age_ranges.append(s)
location_data.school_types_by_age = school_type_age_ranges
return location_data
def get_age_dist_arr(location_data, num_agebrackets=16):
"""
Read in age distribution data from csv files and format the data to add to
the location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
num_agebrackets (int) : the number of age brackets or bins
Returns:
array : An array with dimensions (number of age brackets, 3) with data
on the age distribution.
"""
df = pd.read_csv(
os.path.join(
sp.settings.datadir, location_data.location_name,
f"{location_data.location_name}_ages_{num_agebrackets}.csv"))
age_dist_arr = sp.convert_df_to_json_array(df,
cols=df.columns,
int_cols=['age_min', 'age_max'])
age_dist = sp.PopulationAgeDistribution()
age_dist.num_bins = len(age_dist_arr)
age_dist.distribution = age_dist_arr
return age_dist
def process_enrollment_rates(location_data):
"""
Read in enrollment rates from csv files and format the data to add to the
location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
sp.Location : location_data
"""
raw_data_path = os.path.join(sp.settings.datadir, 'Nepal')
en_df = pd.read_csv(os.path.join(raw_data_path, 'enrollment_by_age.csv'))
age_bin_labels = en_df['Age'].values
binned_rates = en_df['EnrollmentRate'].values
enrollment_rates = dict.fromkeys(np.arange(101), 0)
for bi, bl in enumerate(age_bin_labels):
b = bl.split('-')
b0, b1 = int(b[0]), int(b[1])
for a in range(b0, b1 + 1):
enrollment_rates[a] = binned_rates[bi]
enrollment_rates_df = pd.DataFrame.from_dict(
dict(age=np.arange(len(enrollment_rates)),
percent=[
enrollment_rates[a] for a in sorted(enrollment_rates.keys())
]))
location_data.enrollment_rates_by_age = sp.convert_df_to_json_array(
enrollment_rates_df,
cols=enrollment_rates_df.columns,
int_cols=['age'])
return location_data
def get_household_size_dist_arr(location_data):
"""
Read in household size distribution from csv files and format the data to
add to the location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
array : An array with dimensions (number of household sizes, 2) with data
on the household size distribution.
"""
df = pd.read_csv(os.path.join(sp.settings.datadir, location_data.location_name, f'{location_data.location_name}_household_sizes.csv'))
household_size_dist_arr = sp.convert_df_to_json_array(df, cols=df.columns, int_cols=['household_size'])
return household_size_dist_arr
def process_enrollment_rates(location_data):
"""Process and return enrollment data."""
raw_data_path = os.path.join(sp.settings.datadir, location_data.location_name)
en_df = pd.read_csv(os.path.join(raw_data_path, f'{location_data.location_name}_enrollment_rates_binned_by_age.csv'))
binned_rates = en_df['percent'].values
enrollment_rates = dict.fromkeys(np.arange(101), 0)
for bi in range(len(en_df)):
b0 = en_df['age_min'].values[bi]
b1 = en_df['age_max'].values[bi]
for a in range(b0, b1 + 1):
enrollment_rates[a] = binned_rates[bi]
enrollment_rates_df = pd.DataFrame.from_dict(dict(age=np.arange(len(enrollment_rates)), percent=[enrollment_rates[a] for a in sorted(enrollment_rates.keys())]))
return sp.convert_df_to_json_array(enrollment_rates_df, cols=enrollment_rates_df.columns, int_cols=['age'])
def get_workplace_size_dist_arr(location_data):
"""
Read in workplace size distribution data from csv files and format the data
to add to the location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
array : An array with dimensions (number of workplace size brackets, 3) with data
on the workplace size distribution.
"""
df = pd.read_csv(
os.path.join(sp.settings.datadir, location_data.location_name,
f"{location_data.location_name}_workplace_sizes.csv"))
workplace_size_dist_arr = sp.convert_df_to_json_array(
df,
cols=df.columns,
int_cols=['workplace_size_min', 'workplace_size_max'])
return workplace_size_dist_arr
def get_enrollment_rates_arr(location_data):
"""
Read in enrollment rates from csv files and format the data to add to the
location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
array : An array with dimensions (101, 2) with data
on the enrollment rates for ages 0 through 100.
"""
df = pd.read_csv(
os.path.join(
sp.settings.datadir, location_data.location_name,
f'{location_data.location_name}_enrollment_rates_by_age.csv'))
enrollment_rates_arr = sp.convert_df_to_json_array(df,
cols=df.columns,
int_cols=['age'])
return enrollment_rates_arr
def setup_convert_df_to_json_array(self, pars):
"""
Set up objects to compare.
Args:
pars (dict): dictionary to get the data array and json array for comparison.
Returns:
array, json.array : An array of the desired data from a dataframe and
the json entry for comparison.
"""
df = pd.read_csv(pars.filepath)
# columns to include : include all by default
if pars.cols_ind == []:
cols = df.columns
else:
cols = df.columns[
pars.
cols_ind] # use indices to indicate which columns to include
if pars.int_cols_ind == []:
int_cols = pars.int_cols_ind
else:
int_cols = list(df.columns[pars.int_cols_ind].values)
# array-ify all the data, convert some columns to integers
arr = sp.convert_df_to_json_array(df, cols, int_cols)
# corresponding json data object for the same location and data
location = sp.load_location_from_filepath(f"{pars.location_name}.json")
json_array = getattr(location, pars.property_name)
if pars.property_name == 'population_age_distributions':
json_array = [j for j in json_array
if j.num_bins == len(arr)][0].distribution
return arr, json_array
def process_age_dists(location_data):
"""
Read in age distribution data from csv files and format the data to add to
the location_data json object.
Args:
location_data (sp.Location) : json-based data object for the location
Returns:
sp.Location : location_data
"""
raw_data_path = os.path.join(sp.settings.datadir, 'Nepal')
age_count_df = pd.read_csv(os.path.join(raw_data_path, 'Nepal-2019.csv'))
age_count = np.array(age_count_df['M']) + np.array(age_count_df['F'])
age_dist = age_count / age_count.sum()
age_bin_labels = age_count_df['Age'].values
data = dict()
data['age_min'] = []
data['age_max'] = []
data['age_dist'] = []
for bi, bl in enumerate(age_bin_labels):
try:
b = bl.split('-')
b0, b1 = int(b[0]), int(b[1])
except:
b = bl.split('+')
b0, b1 = int(b[0]), int(b[0])
data['age_min'].append(b0)
data['age_max'].append(b1)
data['age_dist'].append(age_dist[bi])
for k in data:
data[k] = np.array(data[k])
df = pd.DataFrame.from_dict(data)
age_dist_arr = sp.convert_df_to_json_array(df,
cols=df.columns,
int_cols=['age_min', 'age_max'])
location_data.population_age_distributions.append(
sp.PopulationAgeDistribution())
location_data.population_age_distributions[0].num_bins = len(age_dist_arr)
location_data.population_age_distributions[0].distribution = age_dist_arr
data_16 = sc.dcp(data)
data_16['age_min'] = data_16['age_min'][:-5]
data_16['age_max'] = data_16['age_max'][:-5]
data_16['age_max'][-1] = 100
data_16['age_dist'][-6] = data_16['age_dist'][-6:].sum()
data_16['age_dist'] = data_16['age_dist'][:-5]
df_16 = pd.DataFrame.from_dict(data_16)
age_dist_arr_16 = sp.convert_df_to_json_array(
df_16, cols=df_16.columns, int_cols=['age_min', 'age_max'])
location_data.population_age_distributions.append(
sp.PopulationAgeDistribution())
location_data.population_age_distributions[1].num_bins = len(
age_dist_arr_16)
location_data.population_age_distributions[
1].distribution = age_dist_arr_16
return location_data
