def process(self):
df = pd.read_csv(self.filename,
names=self.headers,
na_values=["?"],
quotechar="'")
obj_df = df.copy()
# Process age {numeric}
obj_df["age"] = obj_df["age"].fillna(0)
# Process gender {f,m}
obj_df = pd.get_dummies(obj_df, columns=["gender"], prefix=["is"])
# Process ethnicity {White-European,Latino,Others,Black,Asian,'Middle Eastern ',Pasifika,'South Asian',Hispanic,Turkish,others}
obj_df["ethnicity"] = obj_df["ethnicity"].fillna('')
hee = HashingEncoder(cols=["ethnicity"])
hee.fit(obj_df)
obj_df = hee.transform(obj_df)
# Process jundice {no,yes}
# Process austim {no,yes}
# Process used_app_before {no,yes}
# Class/ASD {NO,YES}
replace_bool = {
"jundice": {
"no": 0,
"yes": 1
},
"austim": {
"no": 0,
"yes": 1
},
"used_app_before": {
"no": 0,
"yes": 1
},
"class": {
"NO": 0,
"YES": 1
},
}
obj_df.replace(replace_bool, inplace=True)
# Process contry_of_res {'United States',Brazil,Spain,Egypt,'New Zealand',Bahamas,Burundi,Austria,Argentina,Jordan,Ireland,'United Arab Emirates',Afghanistan,Lebanon,'United Kingdom','South Africa',Italy,Pakistan,Bangladesh,Chile,France,China,Australia,Canada,'Saudi Arabia',Netherlands,Romania,Sweden,Tonga,Oman,India,Philippines,'Sri Lanka','Sierra Leone',Ethiopia,'Viet Nam',Iran,'Costa Rica',Germany,Mexico,Russia,Armenia,Iceland,Nicaragua,'Hong Kong',Japan,Ukraine,Kazakhstan,AmericanSamoa,Uruguay,Serbia,Portugal,Malaysia,Ecuador,Niger,Belgium,Bolivia,Aruba,Finland,Turkey,Nepal,Indonesia,Angola,Azerbaijan,Iraq,'Czech Republic',Cyprus}
obj_df["contry_of_res"] = obj_df["contry_of_res"].fillna('')
hec = HashingEncoder(cols=["contry_of_res"])
hec.fit(obj_df)
obj_df = hec.transform(obj_df)
# Process age_desc {'18 and more'}
obj_df.drop(columns=["age_desc"], inplace=True)
# Process relation {Self,Parent,'Health care professional',Relative,Others}
obj_df["relation"] = obj_df["relation"].fillna('')
lb_relation = LabelEncoder()
obj_df["relation"] = lb_relation.fit_transform(obj_df["relation"])
self.processed.data = obj_df.values
self.processed.target = np.array(obj_df["class"])
self.processed.target_names = np.array(df["class"].unique())
return self.processed
class _HashingEncoderImpl:
def __init__(self, **hyperparams):
self._hyperparams = hyperparams
self._wrapped_model = SkHashingEncoder(**self._hyperparams)
def fit(self, X, y=None):
self._wrapped_model.fit(X, y)
if isinstance(X, pd.DataFrame):
self._X_columns = X.columns
return self
def transform(self, X):
result = self._wrapped_model.transform(X)
return result