def sum_coding():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.SumEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
def helmert():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.HelmertEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
def polynomial():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.PolynomialEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
def binary():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.BinaryEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
def backward_difference():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.BackwardDifferenceEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
def leaveoneout():
X, _, _ = get_mushroom_data()
print(X.info())
enc = ce.LeaveOneOutEncoder()
enc.fit(X, None)
out = enc.transform(X)
print(out.info())
del enc, _, X, out
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from category_encoders.basen import BaseNEncoder
from examples.source_data.loaders import get_mushroom_data
from sklearn.linear_model import LogisticRegression
import warnings
from sklearn.exceptions import DataConversionWarning
warnings.filterwarnings(action='ignore', category=DataConversionWarning)
print(__doc__)
# first get data from the mushroom dataset
X, y, _ = get_mushroom_data()
X = X.values # use numpy array not dataframe here
n_samples = X.shape[0]
# split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.5,
random_state=0)
# create a pipeline
ppl = Pipeline([('enc', BaseNEncoder(base=2, return_df=False, verbose=True)),
('norm', StandardScaler()),
('clf', LogisticRegression(solver='lbfgs', random_state=0))])
# set the parameters by cross-validation
def control():
X, _, _ = get_mushroom_data()
del X
from __future__ import print_function
from sklearn import datasets
from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import train_test_split
from sklearn.metrics import classification_report
from sklearn.pipeline import Pipeline
from category_encoders.basen import BaseNEncoder
from examples.source_data.loaders import get_mushroom_data
from sklearn.linear_model import LogisticRegression
print(__doc__)
# first we get data from the mushroom dataset
X, y, _ = get_mushroom_data()
X = X.values # use numpy array not dataframe here
n_samples = X.shape[0]
# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)
# create a pipeline
ppl = Pipeline([
('enc', BaseNEncoder(base=2, return_df=False, verbose=True)),
('clf', LogisticRegression())
])
# Set the parameters by cross-validation
tuned_parameters = {