def __init__(self, number_actions, number_sources, number_destinations, number_states, number_hidden_nodes_per_layer, activation_function_type, exploration_type, epsilon, alpha, gamma, beta, learning_rate, learning_method): # Create an instance of the Q_Learning class. self.learn = l.Learn(number_actions, number_sources, number_destinations, number_states, number_hidden_nodes_per_layer, activation_function_type, exploration_type, epsilon, alpha, gamma, beta, learning_rate) self.learning_method = learning_method self.number_actions = number_actions
import criterion import parse import learn import rank if __name__ == "__main__": X = parse.Normalize( '/home/agiachris/CIBCData' ) # Return Dicitonary with States as Keys and databases and values stored_data = [] for key in X.keys(): # Iterate over four datasets print(key) currData = X[key] #currData = currData[:100] # Training spliced datasets stored_data += currData extData = parse.Extract( currData) # Extract required data (doctor type, price) #n = criterion.Number(extData) # Obtain optimal number of Gaussian Components if key == 'NY': score_records = learn.Learn(extData, 50, key) # Cluster, plot, and store else: score_records = np.r_[score_records, (learn.Learn( extData, 50, key))] # Cluster, plot, and store sorted_data = rank.Sort( score_records, stored_data) # Rank dataset according to probability score rank.File1(sorted_data) # Create csv file1 rank.File2(sorted_data) # Create cvs file2
import learn l = learn.Learn("This is a learning program") print(l.share())
def learn_structure(D, Sc, dist = 'multinomial'): S = learn.Learn(D, Sc, 2, dist) spn.save(S, 'spn.net') return S
import learn import neuralnetwork import os import re learn_path = "./new_train" dictionary = learn.Learn(learn_path) condition = True if True else False amount_of_internal_layers = 1 input_len = 5 output_len = 2 important_dict = [] for i in dictionary.common: if dictionary.common[i] > 500: important_dict.append(i) print(len(important_dict)) with open("words", "w") as f: f.write(" ".join(important_dict))