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=74)
# Average CV score on the training set was:0.7005217391304347
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=4, subset_list="module23.csv"),
MinMaxScaler(),
ExtraTreesClassifier(bootstrap=True, criterion="gini", max_features=0.45, min_samples_leaf=8, min_samples_split=8, 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.kernel_approximation import RBFSampler
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=98)
# Average CV score on the training set was:0.693726362625139
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=14, subset_list="subsets.csv"),
RBFSampler(gamma=0.65),
GradientBoostingClassifier(learning_rate=0.5, max_depth=8, max_features=0.6500000000000001, min_samples_leaf=8, min_samples_split=3, n_estimators=100, subsample=0.8500000000000001)
)
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 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=9)
# Average CV score on the training set was:0.7172173913043478
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=12, subset_list="module23.csv"), MinMaxScaler(),
KNeighborsClassifier(n_neighbors=21, p=2, weights="uniform"))
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 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=17)
# Average CV score on the training set was:0.6930515387467556
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"), MinMaxScaler(),
RandomForestClassifier(bootstrap=False,
criterion="gini",
max_features=0.25,
min_samples_leaf=1,
min_samples_split=8,
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 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=22)
# Average CV score on the training set was:0.7259130434782608
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=4, subset_list="module23.csv"), MaxAbsScaler(),
ExtraTreesClassifier(bootstrap=True,
criterion="gini",
max_features=0.4,
min_samples_leaf=4,
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 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=48)
# Average CV score on the training set was:0.6918260869565217
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=4, subset_list="module23.csv"), RobustScaler(),
ExtraTreesClassifier(bootstrap=True,
criterion="entropy",
max_features=0.9500000000000001,
min_samples_leaf=9,
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 ExtraTreesClassifier
from sklearn.model_selection import train_test_split
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=96)
# Average CV score on the training set was:0.7070745272525027
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"), ZeroCount(),
ExtraTreesClassifier(bootstrap=False,
criterion="gini",
max_features=0.8,
min_samples_leaf=1,
min_samples_split=8,
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 StandardScaler
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=0)
# Average CV score on the training set was:0.6939710789766408
exported_pipeline = make_pipeline(
DatasetSelector(sel_subset=0, subset_list="subsets.csv"), StandardScaler(),
GradientBoostingClassifier(learning_rate=0.5,
max_depth=4,
max_features=0.6500000000000001,
min_samples_leaf=7,
min_samples_split=10,
n_estimators=100,
subsample=1.0))
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)