WashingtonGold

from sklearn.cluster import AgglomerativeClustering
model = AgglomerativeClustering(n_clusters=2)
model.fit(X)
model.labels_ #for labels

WashingtonGold

from sklearn.cluster import DBSCAN
model = DBSCAN(eps=0.30, min_samples=9)
model.fit(X)
model.labels_ #for labels of each cluster

WashingtonGold

{'learner': GradientBoostingClassifier(ccp_alpha=0.0, criterion='friedman_mse', init=None,
                           learning_rate=0.009132299586303643, loss='deviance',
                           max_depth=None, max_features='sqrt',
                           max_leaf_nodes=None, min_impurity_decrease=0.0,
                           min_impurity_split=None, min_samples_leaf=1,
                           min_samples_split=2, min_weight_fraction_leaf=0.0,
                           n_estimators=342, n_iter_no_change=None,
                           presort='auto', random_state=2,
                           subsample=0.6844206624548879, tol=0.0001,
                           validation_fraction=0.1, verbose=0,

WashingtonGold

import tpot
pipeline_optimizer = tpot.TPOTClassifier(generations=5, #number of iterations to run the training
                                         population_size=20, #number of individuals to train
                                         cv=5) #number of folds in StratifiedKFold
pipeline_optimizer.fit(X_train, y_train) #fit the pipeline optimizer - can take a long time
print(pipeline_optimizer.score(X_test, y_test)) #print scoring for the pipeline
pipeline_optimizer.export('tpot_exported_pipeline.py') #export the pipeline - in Python code!

WashingtonGold

import autosklearn as ask
#ask.regression.AutoSklearnRegressor() for regression tasks
model = ask.classification.AutoSklearnClassifier(ensemble_size=10, #size of the end ensemble (minimum is 1)
                                                 time_left_for_this_task=120, #the number of seconds the process runs for
                                                 per_run_time_limit=30) #maximum seconds allocated per model
model.fit(X_train, y_train) #begin fitting the search model
print(model.sprint_statistics()) #print statistics for the search
y_predictions = model.predict(X_test) #get predictions from the model

WashingtonGold

model = keras.Model(inputs=[image_input, numerical_input, text_input],
                    outputs=[outputs_1, outputs_2], name='complex model')

WashingtonGold

concat_1 = concatenate([image_text_3, numerical_2])
concat_2 = Dense(16, activation='relu')(concat_1)
outputs_1 = Dense(1, activation='linear', name='continuous')(concat_2) #continuous variable output
outputs_2 = Dense(3, activation='softmax', name='categorical')(concat_2) #categorical variable output

WashingtonGold

from keras.layers import Embedding, LSTM
text_1 = Embedding(10_000, 64)(text_input)
text_2 = LSTM(128)(text_1)

WashingtonGold

from keras.layers import Dense
numerical_1 = Dense(16, activation='relu')(numerical_input)
numerical_2 = Dense(8, activation='relu')(numerical_1)

WashingtonGold

from keras.layers import Conv2D, MaxPooling2D, Flatten
image_1 = Conv2D(32, kernel_size=(3, 3), activation="relu")(image_input) #convolution
image_2 = MaxPooling2D(pool_size=(2, 2))(image_1)                        #max pooling
image_3 = Conv2D(64, kernel_size=(3, 3), activation="relu")(image_2)     #convolution
image_4 = MaxPooling2D(pool_size=(2, 2))(image_3)                        #max pooling
image_5 = Flatten()(image_4)                                             #flatten