def model_iterator(config):
sklearn_models = config['sklearn_models']
sklearn_models = grid_generator.grid_from_classes(sklearn_models,
size=config['grid_size'])
percentiles = config['feature_percentiles']
all_models = list(product(sklearn_models, percentiles))
return all_models
def model_iterator(config):
sklearn_models = config['sklearn_models']
sklearn_models = grid_generator.grid_from_classes(sklearn_models,
size=config['grid_size'])
percentiles = config['feature_percentiles']
all_models = list(product(sklearn_models, percentiles))
return all_models
def model_iterator(config):
classes = [
'sklearn.ensemble.RandomForestClassifier',
'sklearn.ensemble.AdaBoostClassifier'
]
models = grid_generator.grid_from_classes(classes)
return models
from dstools.config import main
from dstools.lab import Experiment
from dstools.lab.util import top_k
from dstools.sklearn import grid_generator
from dstools.sklearn.util import model_name
from sklearn.datasets import load_iris
from sklearn.metrics import precision_score
from sklearn.cross_validation import train_test_split
classes = ["sklearn.ensemble.RandomForestClassifier"]
models = grid_generator.grid_from_classes(classes)
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.30)
# create a new experiment
ex = Experiment(main["logger"])
for m in models:
# create a new record
rec = ex.record()
m.fit(X_train, y_train)
preds = m.predict(X_test)
rec["precision"] = precision_score(y_test, preds)
rec["parameters"] = m.get_params()
rec["model"] = model_name(m)
# select top_k
def model_iterator(config):
classes = ['sklearn.ensemble.RandomForestClassifier',
'sklearn.linear_model.LogisticRegression']
models = grid_generator.grid_from_classes(classes)
return models
from dstools import ExperimentLogger
from dstools.sklearn import grid_generator
from experiment import Experiment
import pandas as pd
# create logger instance
exp_logger = ExperimentLogger()
train_data = pd.read_csv('data/train.csv')
training_x = train_data.drop('survived', axis=1).values
training_y = train_data.survived.values
models = grid_generator.grid_from_classes(['sklearn.ensemble.RandomForestClassifier'])
# ugly mode
for model in models:
model = model.fit(training_x, training_y)
rec = exp_logger.new_record()
rec.add(some_metric)
rec.add(model_name)
rec.add(some_other_metric)
rec.add(feature_set)
rec.add(model_parameters)
# cool kids mode
# using the decorator will log everything that ends with '_log'
# note that using this mode restricts us to save records only from one function
# what if I want to save one record but the data is splitted among several
# functions?
