xiaowei1234

import numpy as np
from sklearn.linear_model import PoissonRegressor, Lasso, Ridge
import statsmodels.api as sm

X_array = np.asarray([[1, 2], [1, 3], [1, 4], [1, 3]])
y = np.asarray([2, 2, 3, 2])
Preg_alpha_1 = PoissonRegressor(alpha=1., fit_intercept=False).fit(X_array, y)
print('alpha 1 Poisson Reg', Preg_alpha_1.coef_)
Preg_alpha_2 = PoissonRegressor(alpha=2., fit_intercept=False).fit(X_array*4., y)
print('alpha 2 Poisson Reg', Preg_alpha_2.coef_)

xiaowei1234

import numpy as np
from sklearn.linear_model import PoissonRegressor, Lasso

X_array = np.asarray([[1, 2], [1, 3], [1, 4], [1, 3]])
y = np.asarray([2, 2, 3, 2])
Preg_alpha_1 = PoissonRegressor(alpha=1., fit_intercept=False).fit(X_array, y)
print('alpha 1', Preg_alpha_1.coef_)
Preg_alpha_2 = PoissonRegressor(alpha=2., fit_intercept=False).fit(X_array/2., y)
print('alpha 2', Preg_alpha_2.coef_)
Lreg_alpha_1 = Lasso(alpha=1., fit_intercept=False).fit(X_array, y)

xiaowei1234

wrap1 = DataFrameMapper([
    ('col_with_nulls', ExpressionTransformer("0 if pandas.isnull(X[0]) else 1")
])

xiaowei1234

from sklearn.pipeline import make_pipeline
from sklearn2pmml.decoration import Alias
from sklearn.pipeline import FeatureUnion


wrap1 = DataFrameMapper([
    ('Status 1', Alias(LookupTransformer({202:1}, 0), 'status_1_202', prefit=True))
    , ('Status 2',  Alias(LookupTransformer({202:1}, 0), 'status_2_202', prefit=True))
    , ('Status 3',  Alias(LookupTransformer({202:1}, 0), 'status_3_202', prefit=True))
])

xiaowei1234

from sklearn.pipeline import make_pipeline

wrap2 = DataFrameMapper([
    ('Status 1', LookupTransformer({203:1}, 0))
    , ('Status 2', LookupTransformer({203:1}, 0))
    , ('Status 3', LookupTransformer({203:1}, 0))
])

union = ExpressionTransformer("X[0]+X[1]+X[2]")

xiaowei1234

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, LabelBinarizer
from sklearn_pandas import DataFrameMapper

col_trans2 = ColumnTransformer([('first', 'drop', [0])]
                               , remainder='passthrough', sparse_threshold=0.0)

mapper = DataFrameMapper([
  ('code1', [CategoricalDomain(missing_value_treatment = "as_value", missing_value_replacement = '!')
             ,LookupTransformer({'a': 'b', 'b': 'd', 'c': 'd'}, 'a')

xiaowei1234

from sklearn2pmml.preprocessing import CutTransformer
from sklearn.impute import SimpleImputer

bins = CutTransformer(bins=[0, 250, 2200], labels=[0.3, 0.4])

wrap = DataFrameMapper([
  ('amount', [SimpleImputer(), bins])
])

xiaowei1234

from sklearn2pmml.decoration import ContinuousDomain
from sklearn.impute import SimpleImputer


cont_d = ContinuousDomain(missing_value_replacement=350, missing_value_treatment='as_value'
                         , missing_values=[float("NaN"), -1], outlier_treatment='as_extreme_values'
                          , low_value=300, high_value=1500)

wrap = DataFrameMapper([
    ('amount', [cont_d, SimpleImputer(), FunctionTransformer(np.log1p, validate=False)])

xiaowei1234

import numpy as np
import pandas as pd
from scipy.stats import ks_2samp
from sklearn.metrics import make_scorer, roc_auc_score, log_loss
from sklearn.model_selection import GridSearchCV

def ks_stat(y, yhat):
    return ks_2samp(yhat[y==1], yhat[y!=1]).statistic

xiaowei1234

def cell_wrapper(df, func, field, drop=True, new_name=None):
    """
    decorator function for pandas pipe api
    takes func which applies function to one value in field
    returns modified dataframe
    df (pandas dataframe): the dataframe to apply transformation on
    func (function): function to apply to each value of field
    field (str): name of column in df
    drop (boolean): whether to drop 'field' after transformation
    new_name (str): whether to rename transformed 'field' column to new_name