def testLinearSVC(self):
ml = ML()
t = Training("classification", "LinearSVC", {
"maxIter": 10,
"regParam": 0.3
}, 0.7, sample_libsvm_data, "./model/svc")
ml.train_model(t)
def testMultilayerPerceptronClassifier(self):
# TODO param layers is neccesary
ml = ML()
t = Training("classification", "MultilayerPerceptronClassifier",
{"layers": [4, 5, 4, 3]}, 0.7,
sample_multiclass_classification_data, "./model/mlp")
print(ml.train_model(t))
def testLogisticRegression(self):
ml = ML()
t = Training(
"classification", "LogisticRegression", {
"maxIter": 10,
"regParam": 0.3,
"elasticNetParam": 0.8,
"family": "multinomial"
}, 0.7, iris, "./model/lr")
ml.train_model(t)
def testCSV(self):
ml = ML()
# ml.compute_statistics(iris, "sepallength")
t = Training(
"classification", "LogisticRegression", {
"maxIter": 10,
"regParam": 0.3,
"elasticNetParam": 0.8,
"family": "multinomial"
}, 0.7, iris, "./model/lr")
# ml.train_model(t)
ml.model_predict_single(t, iris)
def testRandomForestClassifier(self):
ml = ML()
t = Training("classification", "RandomForestClassifier",
{"maxDepth": 10}, 0.7, sample_libsvm_data, "./model/rf")
print(ml.train_model(t))
def testGeneralizedLinearRegression(self):
ml = ML()
t = Training("regression", "GeneralizedLinearRegression",
{"regParam": 0.3}, 0.7, sample_linear_regression_data,
"./model/glr")
print(ml.train_model(t))
def testAFTSurvivalRegression(self):
# TODO not have test data
ml = ML()
t = Training("regression", "AFTSurvivalRegression", {}, 0.7,
sample_libsvm_data, "./model/aftsr")
print(ml.train_model(t))
def testGaussianMixture(self):
ml = ML()
t = Training("clustering", "GaussianMixture", {"maxIter": 99}, 0.7,
sample_kmeans_data, "./model/gm")
print(ml.train_model(t))
def testDecisionTreeRegressor(self):
ml = ML()
t = Training("regression", "DecisionTreeRegressor", {}, 0.7,
sample_libsvm_data, "./model/dtr")
print(ml.train_model(t))
def testIsotonicRegression(self):
ml = ML()
t = Training("regression", "IsotonicRegression", {}, 0.7,
sample_linear_regression_data, "./model/isotonic")
print(ml.train_model(t))
def testLinearRegression(self):
ml = ML()
t = Training("regression", "LinearRegression", {"maxIter": 99}, 0.7,
sample_linear_regression_data, "./model/linear")
print(ml.train_model(t))
"nullable": True,
"type": "double"
}, {
"metadata": {
"label": True
},
"name": "class",
"nullable": True,
"type": "string"
}],
"type":
"struct"
})
# {"fields":[{"metadata":{},"name":"sepallength","nullable":true,"type":"double"},{"metadata":{},"name":"sepalwidth","nullable":true,"type":"double"},{"metadata":{},"name":"petallength","nullable":true,"type":"double"},{"metadata":{},"name":"petalwidth","nullable":true,"type":"double"},{"metadata":{"label":true},"name":"class","nullable":true,"type":"string"}],"type":"struct"}
ml = ML()
# ml.read_source(s)
# schema_json = ml.get_schema_json(s)
# print(schema_json)
# s.schema_json = schema_json
t = Training(
"classification", "LogisticRegression", {
"maxIter": 10,
"regParam": 0.3,
"elasticNetParam": 0.8,
"family": "multinomial"
}, 0.7, s, "./test")
# ml.train_model(t)
ml.model_predict(t, s)
# ml.compute_statistics(s, "sepallength")
def testALS(self):
ml = ML()
t = Training("recommendation", "ALS", {"maxIter": 9}, 0.7, test,
"./model/als")
ml.model_predict_single()
print(ml.train_model(t))
def testLDA(self):
ml = ML()
t = Training("clustering", "LDA", {}, 0.7, sample_lda_libsvm_data,
"./model/lda")
print(ml.train_model(t))
def testBisectingKMeans(self):
ml = ML()
t = Training("clustering", "BisectingKMeans", {}, 0.7,
sample_kmeans_data, "./model/bkmeans")
print(ml.train_model(t))
def testGBTClassifier(self):
ml = ML()
t = Training("classification", "GBTClassifier", {"maxDepth": 10}, 0.7,
sample_libsvm_data, "./model/gbt")
print(ml.train_model(t))
def testNaiveBayes(self):
ml = ML()
t = Training("classification", "NaiveBayes", {"smoothing": 2.0}, 0.7,
sample_libsvm_data, "./model/bayes")
print(ml.train_model(t))
def testRandomForestRegressor(self):
ml = ML()
t = Training("regression", "RandomForestRegressor", {"maxDepth": 5},
0.7, sample_libsvm_data, "./model/rfr")
print(ml.train_model(t))
def testOneVsRest(self):
# TODO param classifier is neccesary
ml = ML()
t = Training("classification", "OneVsRest", {"maxIter": 10}, 0.7,
sample_multiclass_classification_data, "./model/ovr")
print(ml.train_model(t))
def testGBTRegressor(self):
ml = ML()
t = Training("regression", "GBTRegressor", {"maxDepth": 6}, 0.7,
sample_libsvm_data, "./model/gbtr")
print(ml.train_model(t))