def test_search(spark_session):
sc = spark_session.sparkContext
# sklearn variables
Cs = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]
cv = 5
test_size = 0.2
scoring = "roc_auc"
solver = "liblinear"
# load sample data (binary target)
data = load_breast_cancer()
X = data["data"]
y = data["target"]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=test_size,
random_state=10)
### distributed grid search
model = DistGridSearchCV(LogisticRegression(solver=solver),
dict(C=Cs),
sc,
cv=cv,
scoring=scoring)
# distributed fitting with spark
model.fit(X_train, y_train)
# predictions on the driver
preds = model.predict(X_test)
assert preds.shape == y_test.shape
def main():
cv = 5
clf_scoring = "accuracy"
reg_scoring = "neg_mean_squared_error"
data = load_iris()
X = data["data"]
y = data["target"]
grid = dict(learning_rate=[.05, .01],
max_depth=[4, 6, 8],
colsample_bytree=[.6, .8, 1.0],
n_estimators=[100, 200, 300])
model = DistGridSearchCV(XGBClassifier(),
grid,
spark.sparkContext,
cv=cv,
scoring=clf_scoring)
model.fit(X, y)
# predictions on the driver
preds = model.predict(X)
probs = model.predict_proba(X)
# results
print("-- Grid Search --")
print("Best Score: {0}".format(model.best_score_))
print("Best colsample_bytree: {0}".format(
model.best_estimator_.colsample_bytree))
print("Best learning_rate: {0}".format(
model.best_estimator_.learning_rate))
print("Best max_depth: {0}".format(model.best_estimator_.max_depth))
print("Best n_estimators: {0}".format(model.best_estimator_.n_estimators))
def test_gs():
X = np.array([[1, 1, 1], [0, 0, 0], [-1, -1, -1]] * 100)
y = np.array([0, 0, 1] * 100)
gs = DistGridSearchCV(LogisticRegression(solver="liblinear"),
{"C": [0.1, 1.0]},
cv=3)
gs.fit(X, y)
preds = gs.predict(X[:3])
assert np.allclose(preds, np.array([0, 0, 1]))
# instantiate spark session
spark = SparkSession.builder.getOrCreate()
sc = spark.sparkContext
# the digits dataset
digits = datasets.load_digits()
X = digits["data"]
y = digits["target"]
# create a classifier: a support vector classifier
classifier = svm.SVC(gamma="scale")
param_grid = {
"C": [0.01, 0.01, 0.1, 1.0, 10.0],
"gamma": ["scale", "auto", 0.001, 0.01, 0.1],
"kernel": ["rbf", "poly", "sigmoid"],
}
scoring = "f1_weighted"
cv = 10
# hyperparameter optimization
# total fits: 750
start = time.time()
model = DistGridSearchCV(classifier, param_grid, sc=sc, cv=cv, scoring=scoring)
model.fit(X, y)
print("Train time: {0}".format(time.time() - start))
print("Best score: {0}".format(model.best_score_))
results = pd.DataFrame(model.cv_results_).sort_values("mean_test_score",
ascending=False)
print("-- CV Results --")
print(results[["param_C", "param_kernel", "mean_test_score"]].head(10))
df = df[:limit]
dataset["target"] = dataset["target"][:limit]
# fit a small encoder
encoder = Encoderizer(size="small")
X_t = encoder.fit_transform(df)
# train logistic regression
lr = DistGridSearchCV(
LogisticRegression(solver="liblinear"),
dict(C=[0.1, 1.0, 10.0]),
sc,
scoring=scoring,
cv=cv,
)
lr.fit(X_t, dataset["target"])
# train random forest
rf = DistGridSearchCV(
RandomForestClassifier(n_estimators=10),
dict(max_depth=[5, 10]),
sc,
scoring=scoring,
cv=cv,
)
rf.fit(X_t, dataset["target"])
# assemble voter and pipeline
voter = SimpleVoter([("lr", lr), ("rf", rf)],
classes=model.classes_,
voting="hard")
test_size=0.2,
random_state=4)
# initial scaling
scaler = StandardScaler()
X_train_t = scaler.fit_transform(X_train)
X_test_t = scaler.transform(X_test)
# sk-dist logistic regression w/ grid search
start = time.time()
lr = LogisticRegression(solver="lbfgs", multi_class="auto")
model = DistGridSearchCV(lr, {"C": [10.0, 1.0, 0.1, 0.01]},
sc=sc,
cv=5,
scoring="f1_weighted")
model.fit(X_train_t, y_train)
print("-- sk-dist LR --")
print("Train Time: {0}".format(time.time() - start))
print("Best Model CV Score: {0}".format(model.best_score_))
print("Holdout F1: {0}".format(
f1_score(y_test, model.predict(X_test_t), average="weighted")))
# sk-dist random forest
start = time.time()
rf = DistRandomForestClassifier(n_estimators=100, max_depth=None, sc=sc)
rf.fit(X_train_t, y_train)
print("-- sk-dist RF --")
print("Train Time: {0}".format(time.time() - start))
print("Holdout F1: {0}".format(
f1_score(y_test, rf.predict(X_test_t), average="weighted")))
scoring=scoring)
# define word/character vector -> feature selection -> tree ensemble
both_model = Pipeline(steps=[(
"vec",
FeatureUnion([(
"word", CountVectorizer(analyzer="word", decode_error="ignore")
), ("char", CountVectorizer(analyzer="char_wb", decode_error="ignore"))])
), (
"select", SelectKBest(f_classif, 1000)
), ("clf",
DistExtraTreesClassifier(n_estimators=1000, max_depth=None, sc=sc))])
# fit all models
start = time.time()
word_model.fit(X_train, y_train)
print("Word Model Fit Time: {0}".format(time.time() - start))
start1 = time.time()
char_model.fit(X_train, y_train)
print("Char Model Fit Time: {0}".format(time.time() - start1))
start2 = time.time()
both_model.fit(X_train, y_train)
print("Tree Model Fit Time: {0}".format(time.time() - start2))
print("Total Fit Time: {0}".format(time.time() - start))
# construct voter
model = SimpleVoter([("word", word_model), ("char", char_model),
("both", both_model)],
classes=word_model.classes_,
# define encoder config
encoder_config = {
"text_col": "string_vectorizer",
"categorical_str_col": "onehotencoder",
"categorical_int_col": "onehotencoder",
"numeric_col": "numeric",
"dict_col": "dict",
"multilabel_col": "multihotencoder"
}
# variables
Cs = [0.1, 1.0, 10.0]
cv = 5
scoring = "f1_weighted"
solver = "liblinear"
# instantiate encoder with encoder_config, fit/transform on data
encoder = Encoderizer(size="small", config=encoder_config)
df_transformed = encoder.fit_transform(df)
print([i[0] for i in encoder.transformer_list])
# define and fit model
model = DistGridSearchCV(LogisticRegression(solver=solver, multi_class="auto"),
dict(C=Cs),
sc,
scoring=scoring,
cv=cv)
model.fit(df_transformed, df["target"])
print(model.best_score_)
# instantiate a pipeline and grid
pipe = Pipeline(steps=[
("vec", TfidfVectorizer(decode_error="ignore", analyzer="word")),
("svd", TruncatedSVD()),
("clf", LogisticRegression(solver="liblinear", multi_class="auto")),
])
params = {
"clf__C": [0.1, 1.0, 10.0],
"vec__ngram_range": [(1, 1), (1, 2)],
"svd__n_components": [50, 100],
}
# fit and select hyperparameters with skdist
model0 = DistGridSearchCV(pipe, params, sc, scoring=scoring, cv=cv)
model0.fit(X, y)
print("A Pipeline used as the base estimator for DistGridSearchCV: {0}".format(
model0.best_score_))
# assemble a pipeline with skdist distributed
# grid search as the final estimator step
model1 = Pipeline(steps=[
("vec", TfidfVectorizer(decode_error="ignore", analyzer="word")),
("svd", TruncatedSVD(n_components=50)),
(
"clf",
DistGridSearchCV(
LogisticRegression(solver="liblinear", multi_class="auto"),
{"C": [0.1, 1.0, 10.0]},
sc,
scoring=scoring,
solver = "liblinear"
# convert training data to pandas
df = pd.DataFrame({"text": dataset["data"]})
df = df[:1000]
dataset["target"] = dataset["target"][:1000]
# fit a small encoder and train classifier
encoder = Encoderizer(size="small")
X_t = encoder.fit_transform(df)
model = DistGridSearchCV(LogisticRegression(solver=solver, multi_class="auto"),
dict(C=Cs),
sc,
scoring=scoring,
cv=cv)
model.fit(X_t, dataset["target"])
print(model.best_score_)
# fit a medium encoder and train classifier
encoder = Encoderizer(size="medium")
X_t = encoder.fit_transform(df)
model = DistGridSearchCV(LogisticRegression(solver=solver, multi_class="auto"),
dict(C=Cs),
sc,
scoring=scoring,
cv=cv)
model.fit(X_t, dataset["target"])
print(model.best_score_)
# fit a large encoder and train classifier
encoder = Encoderizer(size="large")
