from dstools.util import load_yaml
from dstools.lab import Experiment
import pandas as pd
ex = Experiment(load_yaml('exp.yaml')['conf'])
ex.get(_id=['57435574e0f48c88752991ba'])
best = ex.records[0]
df = pd.DataFrame(best.test_preds, columns=['PassengerId', 'Survived'])
df.set_index('PassengerId', inplace=True)
df.Survived = df.Survived.astype(int)
df.to_csv('res.csv')
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
ex.records = top_k(ex.records, "precision", 2)
from dstools.util import config from dstools.lab import Experiment from dstools.lab.util import group_by ex = Experiment(config['logger']) ex.get(_id=['5744d47f6fdf1e2f69f0716a']) ex.get(key='im super cool') ex.records model = ex.records[0] model['key'] = 'new value2' new_model = ex.record() new_model['key'] = 'im super cool' ex.save() group_by(ex.records, 'model')
from dstools.config import main from dstools.lab import Experiment from dstools.lab.util import group_by, group_map, group_reduce ex = Experiment(main['logger']) ex.get(name=['RandomForestClassifier', 'SVC']) len(ex.records) groups = group_by(ex.records, 'name') maps = group_map(groups, lambda e: e.name) maps group_reduce(maps, lambda x, y: x+y)
