def replace_poisoning_and_suicide(self, df):
df = add_cause_metadata(df, 'acause', cause_meta_df=self.cause_meta_df)
inj_poison = self.cause_meta_df[
self.cause_meta_df.acause ==
"inj_poisoning"]['cause_id'].unique()[0]
inj_suicide = self.cause_meta_df[self.cause_meta_df.acause ==
"inj_suicide"]['cause_id'].unique()[0]
df.loc[df['acause'].str.startswith("inj_poison"),
'cause_id'] = inj_poison
df.loc[df['acause'].str.startswith("inj_suicide"),
'cause_id'] = inj_suicide
df = df[~df['acause'].isin(['inj_homicide', 'inj_trans_road'])]
df = df.drop("acause", axis=1)
return df
def prep_injury_proportions_file(self):
filepath = self.conf.get_resource('injury_proportions')
inj_props = pd.read_csv(filepath)
inj_props = inj_props[inj_props['most_detailed'] == 1]
inj_props = inj_props[['acause', 'rdp2', 'rdp1']]
inj_props = add_cause_metadata(inj_props,
'cause_id',
merge_col='acause',
cause_meta_df=self.cause_meta_df)
inj_props = inj_props.loc[inj_props['cause_id'].notnull()]
inj_props = inj_props.drop('acause', axis=1)
inj_props = pd.melt(inj_props,
id_vars=['cause_id'],
var_name='sex_id',
value_name='prop')
inj_props['sex_id'] = inj_props['sex_id'].apply(lambda x: x[3]).astype(
int)
inj_props['total_prop'] = inj_props.groupby(
'sex_id')['prop'].transform(sum)
inj_props['prop'] = inj_props['prop'] / inj_props['total_prop']
inj_props = inj_props.drop('total_prop', axis=1)
return inj_props
def conform_secret_causes(self, df):
df = add_cause_metadata(df,
add_cols=['secret_cause', 'parent_id'],
cause_meta_df=self.cause_meta_df,
**self.cache_options)
injuries_replace_parents = [722, 720, 719]
replaced_injuries = df['cause_id'].isin(injuries_replace_parents)
df.loc[replaced_injuries, 'parent_id'] = 723
secret_causes = df['secret_cause'] == 1
not_cc_code = df['cause_id'] != 919
len_before = len(df)
if df['parent_id'].isnull().values.any():
raise AssertionError('There are missing parent cause_ids')
df.loc[secret_causes & not_cc_code, 'cause_id'] = df['parent_id']
len_after = len(df)
if len_before != len_after:
raise AssertionError(
'The length of the dataframe has changed from {} to {}'.format(
len_before, len_after))
df.drop(['parent_id', 'secret_cause'], axis=1, inplace=True)
return df