import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.kernel_approximation import Nystroem
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=45)
# Average CV score on the training set was:0.7680533926585095
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"),
Nystroem(gamma=0.25, kernel="polynomial", n_components=9),
ExtraTreesClassifier(bootstrap=False, criterion="gini", max_features=0.9000000000000001, min_samples_leaf=1, min_samples_split=5, n_estimators=100)
)
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.cluster import FeatureAgglomeration
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=50)
# Average CV score on the training set was:0.752695652173913
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=12, subset_list="module23.csv"),
FeatureAgglomeration(affinity="euclidean", linkage="average"),
RandomForestClassifier(bootstrap=False,
criterion="entropy",
max_features=0.45,
min_samples_leaf=9,
min_samples_split=6,
n_estimators=100))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import MinMaxScaler
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=64)
# Average CV score on the training set was:0.7012173913043478
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=4, subset_list="module23.csv"), MinMaxScaler(),
ExtraTreesClassifier(bootstrap=False,
criterion="gini",
max_features=0.9000000000000001,
min_samples_leaf=7,
min_samples_split=20,
n_estimators=100))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import RobustScaler
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=54)
# Average CV score on the training set was:0.680808305524657
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"), RobustScaler(),
RandomForestClassifier(bootstrap=False,
criterion="gini",
max_features=0.55,
min_samples_leaf=6,
min_samples_split=14,
n_estimators=100))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import MaxAbsScaler
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=49)
# Average CV score on the training set was:0.7079495736002966
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"), MaxAbsScaler(),
GradientBoostingClassifier(learning_rate=0.1,
max_depth=5,
max_features=1.0,
min_samples_leaf=1,
min_samples_split=7,
n_estimators=100,
subsample=0.9000000000000001))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import RobustScaler
from tpot.builtins import DatasetSelector
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=90)
# Average CV score on the training set was:0.7012173913043478
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=4, subset_list="module23.csv"), RobustScaler(),
ExtraTreesClassifier(bootstrap=True,
criterion="gini",
max_features=0.8,
min_samples_leaf=16,
min_samples_split=14,
n_estimators=100))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import make_pipeline
from tpot.builtins import DatasetSelector, ZeroCount
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=70)
# Average CV score on the training set was:0.6456507230255839
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=2, subset_list="subsets.csv"), ZeroCount(),
KNeighborsClassifier(n_neighbors=2, p=2, weights="distance"))
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)