def gridsearch(XX, XXpredict, yy, yypredict, clf):
# tuned_parameters=settings.param_grid
param_grid = settings.param_grid
print("Gridsearch start")
def report(grid_scores, n_top=3):
top_scores = sorted(grid_scores, key=itemgetter(1),
reverse=True)[:n_top]
for i, score in enumerate(top_scores):
print("Model with rank: {0}".format(i + 1))
print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
score.mean_validation_score,
numpy.std(score.cv_validation_scores)))
print("Parameters: {0}".format(score.parameters))
print("")
grid_search = GridSearchCV(sc,
clf,
param_grid=param_grid,
cv=10,
n_jobs=-1,
verbose=1)
start = time()
grid_search.fit(XX, yy)
print(
"GridSearchCV took {:.2f} seconds for {:d} candidate settings.".format(
time() - start, len(grid_search.grid_scores_)))
report(grid_search.grid_scores_)
return grid_search
def grid_search_svm(X_train, y_train,X_test,ngrams,n_split,svm_choice='linear',tfidf_choice=False,nums_train=None,nums_test=None):
svm=None
grid=None
if svm_choice == 'linear':
svm = LinearSVC()
c_array = np.logspace(1., 4., num=4)
if tfidf_choice:
grid = {'vect__ngram_range': ngrams, 'tfidf__use_idf': (True, False),
'clf__C': c_array.tolist()}
else:
grid = {'vect__ngram_range': ngrams,
'clf__C': c_array.tolist()}
elif svm_choice == 'svc':
svm = SVC()
c_array = np.logspace(-3., 6., num=10)
g_array = np.logspace(-3., 3., num=7)
if tfidf_choice:
grid = {'vect__ngram_range': ngrams,
'tfidf__use_idf': (True, False),
'clf__kernel': ['rbf'],
'clf__C': c_array.tolist(),
'clf__gamma': g_array.tolist()}
else:
grid = {'vect__ngram_range': ngrams,
'clf__kernel': ['rbf'],
'clf__C': c_array.tolist(),
'clf__gamma': g_array.tolist()}
if type(nums_train) is np.ndarray and type(nums_test) is np.ndarray:
if tfidf_choice:
clf_pipeline = Pipeline([('vect', CountVectorizer(ngram_range=ngrams)),
('tfidf', TfidfTransformer(smooth_idf=False)),
('numfeat', NumFeatureAdder(nums_train,nums_test)),
('clf',svm)])
else:
clf_pipeline = Pipeline([('vect', CountVectorizer(ngram_range=ngrams)),
('numfeat', NumFeatureAdder(nums_train, nums_test)),
('clf', svm)])
else:
if tfidf_choice:
clf_pipeline = Pipeline([('vect', CountVectorizer(ngram_range=ngrams)),
('tfidf', TfidfTransformer(smooth_idf=False)),
('clf',svm)])
else:
clf_pipeline = Pipeline([('vect', CountVectorizer(ngram_range=ngrams)),
('clf',svm)])
print(clf_pipeline.get_params().keys())
sc = SparkContext.getOrCreate()
grid_search = GridSearchCV(sc, clf_pipeline, grid, n_jobs=-1, cv=n_split)
grid_search.fit(X_train, y_train)
grid_search_predicted = grid_search.predict(X_test)
return grid_search_predicted
def train(self, X, y, method="rf"):
param_grid = {
"max_depth": [6, None],
"max_features": [5, 10, 20],
}
obj = RandomForestClassifier()
if method == "svm":
obj = SVC()
self.model = GridSearchCV(RandomForestClassifier(),
param_grid=param_grid)
self.model.fit(X, y)
def grid_search(sc, data, label, features):
"""
使用grid search寻找最优的超参数
"""
# 产生备选的超参数集
parameters = {"alpha": 10**np.linspace(-4, 0, 45)}
# Lasso模型里有超参数alpha，表示惩罚项的权重
la = Lasso()
gs = GridSearchCV(sc, la, parameters)
gs.fit(data[features], data[label])
return gs
def gridSearch(sc, data, label, features):
"""
使用 grid search 寻找最优的超参数
:param sc:
:param data:
:param label:
:param features:
:return:
"""
parameters = {"alpha": 10**np.linspace(-4, 0, 45)}
la = Lasso()
gs = GridSearchCV(sc, la, parameters)
gs.fit(data[features], data[label])
return gs
def main():
"""
main function, runs the program
trains spark sklearn model
"""
absolute_path = "/data/model_data/"
train_df = np.loadtxt(absolute_path + "train.csv", delimiter=',')
train_target_df = np.loadtxt(absolute_path + "target_train.csv", delimiter=',')
test_df = np.loadtxt(absolute_path + "test.csv", delimiter=',')
test_target_df = np.loadtxt(absolute_path + "target_test.csv", delimiter=',')
regr = RandomForestRegressor(random_state=0, n_estimators=1000, min_samples_leaf=1) # best model so far!
# pyspark
regr_rf_cv = GridSearchCV(sc=spark.sparkContext,
estimator=regr,
n_jobs=20,
cv=5,
verbose=5,
param_grid={})
regr_rf_cv.fit(train_df, train_target_df)
y_list, y_hat_list = run_test(test_df, test_target_df, regr_rf_cv)
print("Mean absolute error: {}".format(get_mean_absolute_error(y_list, y_hat_list)))
print("Average relative error: {}".format(get_average_relative_error(y_list, y_hat_list)))
save_model(regr_rf_cv.best_estimator_, "rf_uber_model", "/data/saved_model/")
load_model("/data/saved_model/rf_uber_model.pkl", testExample=(test_df[0], test_target_df[0]))
y_train = targetencoder.transform(gender_age_train['group'])
######################################################
# Training
#######################################################
tuned_parameters = [{'n_estimators': [300,400], 'max_depth': [3,4], 'objective': ['multi:softprob'],
'reg_alpha': [1], 'reg_lambda': [1], 'colsample_bytree': [1],
'learning_rate': [0.1], 'colsample_bylevel': [0.01,0.1],
'subsample': [0.5,0.7]}]
clf = XGBClassifier(seed=0)
metric = 'neg_log_loss'
sc = SparkContext.getOrCreate()
clf_cv = GridSearchCV(sc = sc, param_grid = tuned_parameters, estimator = clf,
scoring=metric, cv=5, verbose=3)
model = clf_cv.fit(X_train,y_train)
run_logger.log(metric, float(clf_cv.best_score_))
for key in clf_cv.best_params_.keys():
run_logger.log(key, clf_cv.best_params_[key])
if not path.exists('./outputs'):
makedirs('./outputs')
outfile = open('./outputs/sweeping_results.txt','w')
print("metric = ", metric, file=outfile)
for i in range(len(model.grid_scores_)):
print(model.grid_scores_[i], file=outfile)
outfile.close()
# Create hold-out test dataset
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
param_grid = {
"max_depth": [3, None],
"max_features": [1, 3, 10],
"min_samples_leaf": [1, 3, 10],
"bootstrap": [True, False],
"criterion": ["gini", "entropy"],
"n_estimators": [10, 20, 40, 80]
}
gs = GridSearchCV(sc=sc,
estimator=RandomForestClassifier(),
cv=4,
param_grid=param_grid,
refit=True)
with timeit():
gs.fit(x_train, y_train)
results = pd.DataFrame(gs.cv_results_)
print(results.sort_values(['mean_test_score'], ascending=False)[0:10])
# Validate accuracy of best model against hold-out data
best_model = gs.best_estimator_
test_accuracy = best_model.score(x_test, y_test)
print(test_accuracy)
logger.log('Best model accuracy', test_accuracy)
max_depth=None).fit(train_data, train_labels)
RF_calibrated_and_tuned_pre_fit = CalibratedClassifierCV(RF_tuned,
method='isotonic',
cv='prefit')
RF_calibrated_and_tuned = RF_calibrated_and_tuned_pre_fit.fit(
calibration_data, Calibration_labels)
param_grid = {
"base_estimator": [RF_calibrated_and_tuned],
"n_estimators": [i for i in range(1, 1001, 1)],
"max_samples": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12],
"max_features":
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20],
"bootstrap": [True, False],
"bootstrap_features": [True, False],
"oob_score": [True, False]
}
clf = BaggingClassifier()
# bagging_fitted = clf.fit(train_data,train_labels)
# bagging_prediction_probabilities = bagging_fitted.predict_proba(dev_data)
# log_loss_for_RF_tuned_calibrated_bagged = log_loss(y_true = dev_labels, y_pred = bagging_prediction_probabilities, labels = crime_labels)
# print("Multi-class Log Loss with RF tuned calibrated and bagged is:", log_loss_for_RF_tuned_calibrated_bagged)
gs = GridSearchCV(sc, clf, param_grid) # add "n_jobs?"
start = time()
gs.fit(mini_train_data, mini_train_labels)
print("GridSearchCV took {:.2f} seconds for {:d} candidate settings.".format(
time() - start, len(gs.grid_scores_)))
report(gs.grid_scores_)
19000:28000]
mini_dev_data, mini_dev_labels = X_final[49000:60000], y_final[49000:60000]
param_grid = {
'learning_rate': [0.05, 0.01, 0.005, 0.001],
'n_iter': [25, 50, 100, 200],
'hidden0__units': [4, 8, 12, 16, 20],
'hidden0__type': ["Rectifier", "Sigmoid", "Tanh"],
'hidden0__dropout': [0.2, 0.3, 0.4],
'hidden1__units': [4, 8, 12, 16, 20],
'hidden1__type': ["Rectifier", "Sigmoid", "Tanh"],
'hidden1__dropout': [0.2, 0.3, 0.4],
'hidden2__units': [4, 8, 12, 16, 20],
'hidden2__type': ["Rectifier", "Sigmoid", "Tanh"],
'hidden2__dropout': [0.2, 0.3, 0.4]
}
nn = Classifier(layers=[
Layer("Sigmoid", units=20),
Layer("Sigmoid", units=20),
Layer("Sigmoid", units=20),
Layer("Softmax")
])
gs = GridSearchCV(sc, nn, param_grid)
start = time()
gs.fit(mini_train_data, mini_train_labels)
print("GridSearchCV took {:.2f} seconds for {:d} candidate settings.".format(
time() - start, len(gs.grid_scores_)))
report(gs.grid_scores_)
xgb_params = {
'eta': 0.05,
'max_depth': 6,
'subsample': 0.7,
'colsample_bytree': 0.7,
'objective': 'reg:linear',
'silent': 1
}
import xgboost as xgb
dtrain = xgb.DMatrix(train_X, train_y, feature_names=train_X.columns.values)
model = xgb.train(dict(xgb_params, silent=0), dtrain, num_boost_round=100, feval=xgb_r2_score, maximize=True)
# Gradient Boosting Regressor
gbr = ensemble.GradientBoostingRegressor()
clf = GridSearchCV(gbr, cv=3, param_grid=tuned_parameters,
scoring='median_absolute_error')
preds = clf.fit(X_train, y_train)
best = clf.best_estimator_
# plot error for each round of boosting
# Note: best_estimator_, staged_predict
test_score = np.zeros(n_est, dtype=np.float64)
train_score = best.train_score_
for i, y_pred in enumerate(best.staged_predict(X_test)):
test_score[i] = best.loss_(y_test, y_pred)
### Grid search
from pyspark import SparkContext, SparkConf
from spark_sklearn import GridSearchCV
sc = SparkContext(conf=conf)
digits = load_digits()
n_samples = len(digits.images)
data = digits.images.reshape((n_samples, -1))
X_train, X_test, y_train, y_test = train_test_split(data, digits.target, test_size=0.3, random_state=0)
svc = svm.SVC()
hyperparam_grid = {
'kernel': ['linear', 'poly', 'rbf', 'sigmoid'],
'gamma': np.linspace(0.001, 0.01, num=10),
'C': np.linspace(1, 10, num=10),
'tol': np.linspace(0.01, 0.1, 10)
}
classifier = GridSearchCV(sc, svc, hyperparam_grid)
start = time()
classifier.fit(X_train, y_train)
elapsed = time() - start
print('elapsed: {} seconds'.format(elapsed))
print('Best Kernel:\t{}'.format(classifier.best_estimator_.kernel))
print('Best Gamma:\t{}'.format(classifier.best_estimator_.gamma))
print('Best C:\t\t{}'.format(classifier.best_estimator_.C))
y_pred = classifier.predict(X_test)
print('Accuracy:\t{:.1%}'.format(metrics.accuracy_score(y_test, y_pred)))
X_minus_trea = X[np.where(y != 'TREA')]
y_minus_trea = y[np.where(y != 'TREA')]
X_final = X_minus_trea[np.where(y_minus_trea != 'PORNOGRAPHY/OBSCENE MAT')]
y_final = y_minus_trea[np.where(y_minus_trea != 'PORNOGRAPHY/OBSCENE MAT')]
# Separate training, dev, and test data:
test_data, test_labels = X_final[800000:], y_final[800000:]
dev_data, dev_labels = X_final[700000:800000], y_final[700000:800000]
train_data, train_labels = X_final[100000:700000], y_final[100000:700000]
calibrate_data, calibrate_labels = X_final[:100000], y_final[:100000]
# Create mini versions of the above sets
mini_train_data, mini_train_labels = X_final[:20000], y_final[:20000]
mini_calibrate_data, mini_calibrate_labels = X_final[19000:28000], y_final[
19000:28000]
mini_dev_data, mini_dev_labels = X_final[49000:60000], y_final[49000:60000]
param_grid = {
'C': [.001, .01, .01] + [i for i in range(1, 100, 5)],
"penalty": ['l1', 'l2']
}
clf = LogisticRegression()
gs = GridSearchCV(sc, clf, param_grid)
start = time()
gs.fit(mini_train_data, mini_train_labels)
print("GridSearchCV took {:.2f} seconds for {:d} candidate settings.".format(
time() - start, len(gs.grid_scores_)))
report(gs.grid_scores_)
SPARK_HOME + 'python/lib/pyspark.zip',
SPARK_HOME + 'python/lib/py4j-0.10.1-src.zip']
)
from pyspark import SparkContext
from pyspark import SparkConf
if __name__ == '__main__':
conf = SparkConf()
conf.setMaster("local[3]")
# 指定具体的Master机器 地址和端口
# conf.setMaster("spark://jdwang-HP:7077")
conf.setAppName("spark_test")
# 可以设置属性等
# conf.set("spark.executor.memory", "12g")
sc = SparkContext(conf=conf)
# 测试
from sklearn import svm, datasets
from spark_sklearn import GridSearchCV
iris = datasets.load_iris()
parameters = {'kernel': ('linear', 'rbf'), 'C': [1, 10]}
svr = svm.SVC()
clf = GridSearchCV(sc, svr, parameters)
clf.fit(iris.data, iris.target)
print(clf.best_params_)
print(clf.predict(iris.data))
end_time = time.time()
print('running time is %ds'%(end_time-start_time))
print(y_train.shape)
# COMMAND ----------
# MAGIC %md Create SVC Model
# COMMAND ----------
from sklearn import svm, grid_search, datasets
from spark_sklearn import GridSearchCV
parameters = {
'kernel': ('linear', 'rbf', 'poly', 'rbf', 'sigmoid'),
'C': [1, 20]
}
svr = svm.SVC()
clf = GridSearchCV(sc, svr, param_grid=parameters, scoring='accuracy')
clf.fit(x_train, y_train)
print(clf.best_params_)
bestsvc = clf.best_estimator_
print(clf.best_score_)
# COMMAND ----------
# MAGIC %md Create Random Forest Model
# COMMAND ----------
en_rf = RandomForestClassifier(n_estimators=64,
max_depth=32,
min_samples_split=128,
random_state=0)
# MAGIC - `normalize`. True or False.The regressors X will be normalized before regression by subtracting the mean and dividing by the l2-norm or by their standard deviations.
# MAGIC - `alpha`. It represents the regularization strength; Regularization improves the conditioning of the problem and reduces the variance of the estimates. Here we chose a range (0.001, 1000).
# MAGIC
# MAGIC Then cross validation is defined as 5 time series splits which means it will train the model on combination of 4 subsets created from the training datset and validate the trained model on one subset. And the scoring method is R square which is a statistical measure of how close the data are to the fitted regression line. Then fit the gridsearchcv with features and target datasets
# COMMAND ----------
from spark_sklearn import GridSearchCV
from sklearn.model_selection import TimeSeriesSplit
from sklearn.metrics import make_scorer, mean_absolute_error, r2_score
lasso_run = \
GridSearchCV(sc,
estimator=get_lasso_pipeline(),
param_grid={'lso__normalize':[True,False],
'lso__alpha' :[10.0**n for n in range(-3,4)]},
cv=TimeSeriesSplit(n_splits=5),
scoring=make_scorer(r2_score),
return_train_score=False,
n_jobs=-1
)
lasso_run.fit(trn_coal_cnt_fea_pdf, trn_coal_cnt_tgt_ser)
display_pdf(est_grid_results_pdf(lasso_run,
est_tag='lasso'))
# COMMAND ----------
lasso_run.fit(trn_ore_tfidf_fea_pdf, trn_ore_tfidf_tgt_ser)
display_pdf(est_grid_results_pdf(lasso_run,
from sklearn import grid_search
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from spark_sklearn import GridSearchCV
df = pd.read_csv('../data/master_RushPassOnly.csv')
y = df.pop('IsPass').values
X = df.values
param_grid = {
"max_depth": [3, 5, 10, None],
"max_features": [None, 'auto', 'log2'],
"n_estimators": [100],
'min_samples_split': [2, 4],
'min_samples_leaf': [1, 2, 4],
'bootstrap': [True, False]
}
rf = RandomForestClassifier(verbose=2, n_jobs=-1)
gs = GridSearchCV(rf,
param_grid=param_grid,
n_jobs=-1,
verbose=2,
scoring='neg_mean_squared_error')
gs.fit(X, y)
best_parameters = gs.best_params_
print best_parameters
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import load_boston
from spark_sklearn import GridSearchCV
import pyspark
if __name__ == '__main__':
sc = pyspark.SparkContext('local[*]')
boston = load_boston()
RAMDON_FOREST_PARAMS = {
"n_estimators": [100],
"max_features": [1, "auto", "sqrt", None],
"max_depth": [1, 5, 10, None],
"min_samples_leaf": [1, 2, 4, 50]
}
rf = RandomForestRegressor(random_state=0, n_jobs=-1)
clf = GridSearchCV(sc, rf, RAMDON_FOREST_PARAMS)
clf.fit(boston.data, boston.target)
print("parameters for random forest: {0}".format(clf.best_params_),
sep="\n")
from dl_steer import dt_handler, coordinator, custom_model, engine_interface, provenance
from keras.wrappers.scikit_learn import KerasClassifier
from spark_sklearn import GridSearchCV
from keras.models import Sequential
data = dt_handler.read_dataset('input_data.csv')
...
model = KerasClassifier(build_fn=custom_model.get_model(), verbose=0)
X, y = data['X'], data['y']
queue = coordinator.get_queue()
for hyperparameter_combination in queue:
provenance.persist(hyperparameter_combination)
grid = GridSearchCV(estimator=model,
param_grid=hyperparameter_combination,
n_jobs=-1,
scoring="accuracy")
grid_result = grid.fit(X, y)
provenance.persist(grid_result)
#The method below verifies if user steered the queue. If yes, it reloads the queue accordingly.
queue.checkSteering()
j = exec_config[0]
print('----------------- Config = ', j, ' -------------------------')
conf = sc._conf.setAll([('spark.executor.memory', j[0]),
('spark.executor.cores', j[1]),
('spark.executor.instances', j[2])])
spark = SparkSession.builder.config(conf=conf).getOrCreate()
print(sc._conf.getAll())
for i in iter_list:
print('--------------------Iterations = ', i, '-----------------------')
param_grid = {
"solver": ["sgd"],
"max_iter": [i],
"hidden_layer_sizes": [(100, 10)],
}
gs = GridSearchCV(sc, estimator=MLPClassifier(), param_grid=param_grid)
print('Time info for iterations = ', i)
get_ipython().run_line_magic('time', 'gs.fit(train, y_train)')
preds = gs.predict(test)
print('Accuracy=', np.sum(y_test == preds) * 100 / len(y_test), '%')
#### CONFIG 2 ########
j = exec_config[1]
print('----------------- Config = ', j, ' -------------------------')
conf = sc._conf.setAll([('spark.executor.memory', j[0]),
('spark.executor.cores', j[1]),
('spark.executor.instances', j[2])])
spark = SparkSession.builder.config(conf=conf).getOrCreate()
print(sc._conf.getAll())
def test():
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.ensemble import GradientBoostingClassifier
# from sklearn.model_selection import GridSearchCV
from spark_sklearn import GridSearchCV
from pyspark import SparkConf, SparkContext, HiveContext
from spark_sklearn import Converter
import time
start = time.time()
conf = SparkConf().setAppName("spark-sklearn")
sc = SparkContext(conf=conf)
spark = HiveContext(sc)
path = "/home/data/data_cell_lable_0521_rsrp_five3_all.csv"
df = spark.read.csv(path, header=True, inferSchema=True)
converter = Converter(sc)
df_data = converter.toPandas(df)
# 也可以直接使用 pandas的DataFrame进行操作
# inputpath1 = '/home/etluser/xiexiaoxuan/data/data_cell_lable_0521_rsrp_five3_all.csv'
# df_data = pd.read_csv(inputpath1)
df_data = df_data.dropna(axis=0, how='any')
x1 = df_data.drop(['label'], axis=1)
y1 = df_data['label']
gbm0 = GradientBoostingClassifier(n_estimators=262,
max_depth=57,
min_samples_split=50,
random_state=10,
subsample=0.7,
learning_rate=0.01)
pipeline = Pipeline([("standard", StandardScaler()), ("gbdt", gbm0)])
params = {
"gbdt__n_estimators": [i for i in range(10, 20)],
"gbdt__max_depth": [i for i in range(3, 20)]
}
grid_search = GridSearchCV(sc,
pipeline,
param_grid=params,
error_score=0,
scoring="accuracy",
cv=5,
n_jobs=10,
pre_dispatch="2*n_jobs",
return_train_score=False)
grid_search.fit(x1, y1)
end = time.time()
print("总耗时 ：%.2f s" % (end - start))
print(grid_search.best_estimator_)
index = grid_search.best_index_
res = grid_search.cv_results_
best_score = res["mean_test_score"][index]
print("===============: " + str(best_score))
documentDF = session.createDataFrame([
("Hi I heard about Spark", "spark"),
("I wish Java could use case classes", "java"),
("Logistic regression models are neat", "mlib"),
("Logistic regression models are neat", "spark"),
("Logistic regression models are neat", "mlib"),
("Logistic regression models are neat", "java"),
("Logistic regression models are neat", "spark"),
("Logistic regression models are neat", "java"),
("Logistic regression models are neat", "mlib")
], ["text", "preds"]).select(f.split("text", "\\s+").alias("new_text"), "preds")
word2vec = Word2Vec(vectorSize=100, minCount=1, inputCol="new_text",
outputCol="features")
indexer = StringIndexer(inputCol="preds", outputCol="labels")
pipline = Pipeline(stages=[word2vec, indexer])
ds = pipline.fit(documentDF).transform(documentDF)
data = ds.toPandas()
parameters = {'kernel': ('linear', 'rbf')}
svr = svm.SVC()
clf = GridSearchCV(session.sparkContext, svr, parameters)
X = [x.values for x in data.features.values]
y = [int(x) for x in data.labels.values]
model = clf.fit(X, y)
# modelB = session.sparkContext.broadcast(pickle.dumps(model))
# wow = documentDF.rdd.map(lambda row: pickle.loads(modelB.value).transform(row["features"].values)).collect()
# print(wow)
Y_timetrain_arr = np.ravel(Y_timetrain)
X_timetest = X.loc[X.index >= 398]
Y_timetest = y.loc[y.index >= 398]
Y_timetest_arr = np.ravel(Y_timetest)
X_timetest
# In[99]:
tuned_parameters = {
"n_estimators": [ 100 ],
"max_depth" : [ 3 ],
"learning_rate": [ 0.1 ],
}
gbc = ensemble.GradientBoostingClassifier()
clf = GridSearchCV(spark.sparkContext, gbc, tuned_parameters)
clf
# In[100]:
clf.fit(X_timetrain, Y_timetrain_arr)
clftest_pred = clf.predict(X_timetest)
print "Accuracy is ", metrics.accuracy_score(Y_timetest_arr, clftest_pred) *100, "%"
# In[101]:
knn1 = KNeighborsClassifier()
knn_params = {
"n_neighbors": [31]
def call_GridSearchCV(model, praram_grid):
GridSearchCV(sc, model, param_grid=param_grid)
target_names=le.classes_)
tuned_parameters = {
"max_depth": [3, None],
"max_features": [1, 'auto'],
"min_samples_split": [1, 20],
"n_estimators": [10, 300, 500]
}
rf = RandomForestClassifier(random_state=rs)
# spark-sklearn
conf = SparkConf()
sc = SparkContext(conf=conf)
clf = GridSearchCV(sc,
rf,
cv=3,
param_grid=tuned_parameters,
scoring='accuracy')
# scikit-learn
# clf = GridSearchCV(rf, cv=2, scoring='accuracy',
# param_grid=tuned_parameters,
# verbose=True)
preds = clf.fit(X_train, y_train)
best = clf.best_estimator_
this_score = metrics.accuracy_score(y_test, best.predict(X_test))
scorestr = "RF / GridSearchCV: Accuracy Score %0.2f" % this_score
print
print scorestr
print "-" * len(scorestr)
