Last active
January 17, 2018 01:15
-
-
Save alucard001/97b55f7361cb0089b9466e57e99d5737 to your computer and use it in GitHub Desktop.
Using TPOT Classifier to analysis Numerai dataset
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Largely come from TPOT example. The only control you can do to prevent timeout | |
and successful running is the "generation" and "population_size" parameters. | |
Remember, scoring is "log_loss" as of 18 Jan 2017, not probability | |
The larger the generation and population_size, the longer time you take to get result. | |
""" | |
from tpot import TPOTClassifier | |
from sklearn.model_selection import train_test_split | |
import pandas as pd | |
data = pd.read_csv("numerai_training_data.csv") | |
X, y = data.iloc[:,0:49], data.iloc[:,50] | |
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.75, test_size=0.25) | |
tpot = TPOTClassifier(generations=4, population_size=20, verbosity=2, scoring="log_loss") | |
tpot.fit(X_train, y_train) | |
print(tpot.score(X_test, y_test)) | |
tpot.export('tpot_numerai_pipeline.py') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
When using generation = 3 | |
""" | |
import numpy as np | |
from sklearn.ensemble import VotingClassifier | |
from sklearn.model_selection import train_test_split | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.pipeline import make_pipeline, make_union | |
from sklearn.preprocessing import FunctionTransformer | |
# NOTE: Make sure that the class is labeled 'class' in the data file | |
tpot_data = np.recfromcsv('PATH/TO/DATA/FILE', delimiter='COLUMN_SEPARATOR', dtype=np.float64) | |
features = np.delete(tpot_data.view(np.float64).reshape(tpot_data.size, -1), tpot_data.dtype.names.index('class'), axis=1) | |
training_features, testing_features, training_classes, testing_classes = \ | |
train_test_split(features, tpot_data['class'], random_state=42) | |
exported_pipeline = make_pipeline( | |
MultinomialNB(alpha=0.1, fit_prior=True) | |
) | |
exported_pipeline.fit(training_features, training_classes) | |
results = exported_pipeline.predict(testing_features) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
When using generation = 4 | |
""" | |
import numpy as np | |
from sklearn.ensemble import VotingClassifier | |
from sklearn.model_selection import train_test_split | |
from sklearn.naive_bayes import GaussianNB, MultinomialNB | |
from sklearn.pipeline import make_pipeline, make_union | |
from sklearn.preprocessing import FunctionTransformer, MinMaxScaler | |
# NOTE: Make sure that the class is labeled 'class' in the data file | |
tpot_data = np.recfromcsv('PATH/TO/DATA/FILE', delimiter='COLUMN_SEPARATOR', dtype=np.float64) | |
features = np.delete(tpot_data.view(np.float64).reshape(tpot_data.size, -1), tpot_data.dtype.names.index('class'), axis=1) | |
training_features, testing_features, training_classes, testing_classes = \ | |
train_test_split(features, tpot_data['class'], random_state=42) | |
exported_pipeline = make_pipeline( | |
make_union( | |
FunctionTransformer(lambda X: X), | |
FunctionTransformer(lambda X: X) | |
), | |
MinMaxScaler(), | |
make_union(VotingClassifier([("est", GaussianNB())]), FunctionTransformer(lambda X: X)), | |
MultinomialNB(alpha=0.71, fit_prior=True) | |
) | |
exported_pipeline.fit(training_features, training_classes) | |
results = exported_pipeline.predict(testing_features) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment