def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.skew_info = compute_df_skew(X[self.cols_lst])
self.status = True
def fit(self, X, y):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [col for col in self.cols_lst if col in X.columns]
self.woe_info = f_df_woe(X[self.cols_lst], y)
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type='str')
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.nunique_cnt = compute_df_nunique_cnt(X[self.cols_lst])
self.var_filter = {
k: v
for k, v in self.nunique_cnt.items() if v == self.filter_thres
}
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.null_rate = compute_df_null_rate(X[self.cols_lst])
self.fill_info = self.fill_value_fun[self.fill_type](X, self.cols_lst)
for col in self.cols_lst:
if self.null_rate[col] >= self.fill_thres:
self.fill_info[col] = 'null'
def fit(self, X, y):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.to_list()
]
self.iv_info = f_df_iv(X[self.cols_lst], y)
self.var_filter = {
k: v
for k, v in self.iv_info.items() if v < self.iv_thres
}
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
#self.LabelEncoders = {col:LabelEncoder() for col in self.cols_lst}
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.LabelEncoders = {col: LabelEncoder() for col in self.cols_lst}
for col in self.cols_lst:
self.LabelEncoders[col].fit(X[col])
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
if y is None:
y = X[self.y]
self.var_importance = computer_df_importance_xgb_regressor(
X[self.cols_lst], y)
self.var_filter = {
k: v
for k, v in self.var_importance.items() if v <= self.filter_thres
}
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.bin_info = f_df_str_chisq_group(X=X[self.cols_lst],
y=y,
p_value=self.p_value,
pct=self.pct,
max_groups=self.max_groups,
num_least=self.num_least)
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.MinMaxScalers = {
col: MinMaxScaler(feature_range=self.feature_range)
for col in self.cols_lst
}
for col in self.cols_lst:
self.MinMaxScalers[col].fit(X[col].values.reshape(-1, 1))
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
if y is None:
y = X[self.y]
self.corr_info = compute_df_corr(X[self.cols_lst], y)
self.var_filter = {
k: v
for k, v in self.corr_info.items() if abs(v) < self.filter_thres
}
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
#self.OneHotEncoders = {col:OneHotEncoder(handle_unknown = 'ignore') for col in self.cols_lst}
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.OneHotEncoders = {
col: OneHotEncoder(handle_unknown='ignore')
for col in self.cols_lst
}
for col in self.cols_lst:
self.OneHotEncoders[col].fit(X[col].values.reshape(-1, 1))
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = select_var_by_type(X,
uid=self.uid,
y=self.y,
var_type=self.require_var_type)
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
self.StandardScalers = {
col: StandardScaler(copy=False,
with_mean=self.with_mean,
with_std=self.with_std)
for col in self.cols_lst
}
for col in self.cols_lst:
self.StandardScalers[col].fit(X[col].values.reshape(-1, 1))
self.fit_status = True
def fit(self, X, y=None):
if len(self.cols_lst) == 0:
self.cols_lst = [
col for col in select_var_by_type(
X, uid=self.uid, y=self.y, var_type=['int', 'float'])
]
else:
self.cols_lst = [
col for col in self.cols_lst if col in X.columns.tolist()
]
if self.bin_type == 'dtree':
self.cut_info = self.bin_fun[self.bin_type](
X[self.cols_lst],
y=y,
criterion=self.criterion,
min_samples_leaf=self.min_samples_leaf,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease)
elif self.bin_type == 'chisq':
self.cut_info = self.bin_fun[self.bin_type](
X[self.cols_lst],
y=y,
p_value=self.p_value,
pct=self.pct,
max_groups=self.max_groups,
num_least=self.num_least)
elif self.bin_type in ['quantile', 'equal_width']:
self.cut_info = self.bin_fun[self.bin_type](X[self.cols_lst],
self.q)
else:
raise ValueError('bin_type参数只支持dtree、chisq、quantile和equal_width值')
self.fit_status = True
