'Please input the classweight of the decision tree(** ** ** **):')
classweight = [int(item) for item in classweight.split()]
wei = []
if classweight[0] == 0:
wei.append('balanced')
elif classweight[0] == 1028:
wei.append(1028)
else:
wei.append({0: classweight[0], 1: classweight[1]})
if classweight[2] == 0:
wei.append('balanced')
elif classweight[2] == 1028:
wei.append(1028)
else:
wei.append({0: classweight[2], 1: classweight[3]})
data, label, timeind = function.load_data('f60-23-1119.xlsx', N)
data2, label2, timeind2 = function.load_data('f10-23-1119.xlsx', N)
N = len(data)
# # data, label, timeind = function.createdataset(data, label, timeind, 0.5, N, 5)
# # # data2, label2 = function.createdataset(data2, label2, 0.5, N, 2)
# indall = [i for i in range(23)]
# indall = set(indall)
# # indfew = [4,5,6,8,10,12,14,15,16]
# indfew = [12]
# # indfew = []
# indfew = set(indfew)
# indroi = indall - indfew
# indroi = list(indroi)
# # # indroi = [0,1,2,7,9,11,13,14,21]
# ind = np.array(indroi)
import numpy as np from function import load_data from sklearn.linear_model import LogisticRegression from sklearn.preprocessing import MinMaxScaler from sklearn.decomposition import PCA from sklearn.model_selection import KFold from sklearn.metrics import accuracy_score """ ロジスティック回帰を用いて，音声ファイルを2クラスに分類する 10-foldクロスバリデーションより、分類の精度をみる ランダムに2クラス分類を行った場合と比較する """ csv_file_path = r"path/to/data.csv" x_data, y_data = load_data(csv_file_path) x_data = np.array(x_data) y_data = np.array(y_data) # データを10分割する n_fold = 10 k_fold = KFold(n_fold, shuffle=True) accuracy_list = [] train_accuracy_list = [] norm_accuracy_list = [] norm_train_accuracy_list = [] L1_accuracy_list = [] L1_train_accuracy_list = [] PCA_accuracy_list = []
import function as f
import time
filename = '2017.12.11 Dataset Project 2.csv'
C = 6.5
gamma = 0.24
X, Y = f.load_data(filename)
Xtr, Xtst, Ytr, Ytst = f.split_data(X, Y)
def main():
t = time.time()
alpha_star, res = f.find_alpha_star(Xtr, Ytr, C, gamma)
totalTime = time.time() - t
b_star = f.find_b_star(alpha_star, Xtr, Ytr, C, gamma)
#print("b_star: ", b_star)
ytstpred = f.predict(alpha_star, b_star, Xtr, Ytr, Xtst, gamma)
ytrpred = f.predict(alpha_star, b_star, Xtr, Ytr, Xtr, gamma)
test_accuracy = f.acc_score(ytstpred, Ytst)
#print("Main train accuracy: ",f.acc_score(ytrpred,Ytr))
output = open("output_homework2_28.txt",
"a") # instead of 99, number of the team
output.write("Homework 2, question 1")
output.write("\nTraining objective function," + "%f" % res.fun)
from spacetime.client.declarations import Producer, GetterSetter, Getter
from lxml import html,etree
import re, os
from time import time
from uuid import uuid4
from urlparse import urlparse, parse_qs
from uuid import uuid4
# store all the global varaibles
from function import save_data, load_data
import json
# loading global variable
file_name = 'data.txt'
pages_count, MaxOutputLink, invalid_count, subdomain = load_data(file_name)
logger = logging.getLogger(__name__)
LOG_HEADER = "[CRAWLER]"
@Producer(PaichunwLink)
@GetterSetter(OnePaichunwUnProcessedLink)
class CrawlerFrame(IApplication):
app_id = "Paichunw"
def __init__(self, frame):
#self.starttime = time()
self.app_id = "Paichunw"
self.frame = frame
pa = ap.parse_args() where = pa.data_dir path = pa.save_dir lr = pa.learning_rate save_dir = pa.save_dir dropout = pa.dropout power = pa.gpu epochs = pa.epochs architecture = pa.pretrained_model hiddenl = pa.hidden_units trainloader, validloader, testloader, train_data, valid_data, test_data = load_data(where) pretr_model = pa.pretrained_model model = getattr(models, pretr_model)(pretrained = True) build_classifier(model) build_classifier(model) criterion = nn.NLLLoss() optimizer = optim.Adam(model.classifier.parameters(),lr=0.0001) model, optimizer = train_model(model, epochs, trainloader, validloader, criterion, optimizer, power, lr, hiddenl, dropout) test_model(model, testloader) save_model(model, train_data, optimizer, save_dir, epochs, lr, architecture, hiddenl, dropout)
]
result_eva.append(tmp)
# ******************************1.parameters setting***************************
feature_num = 128 #number of features: ecg+pcg 64 + 64
group_num = 400 #number of feature subset in population
best_feature = [] #the optimal subset
best_score = 0 #the score of optimal subset
times = 0
group = [[random.randint(1, 2) for i in range(feature_num)]
for j in range(group_num)] #生成初始种群
for each1 in range(len(group)):
for each2 in range(len(group[each1])):
if group[each1][each2] > 0:
group[each1][each2] = 1
# ****************************** 2.data loading ***************************
x_train, y_train, x_test, y_test = function.load_data(params)
#scaler.fit_transform(np.vstack([x_train,x_test]))
# ****************************** 3.genetic algorithm
schedule = range(0, 100, 1)
for sch in tqdm.tqdm(schedule):
score = []
for i in range(group_num):
x_train_tmp = fea_gene_generator(group[i], x_train)
x_test_tmp = fea_gene_generator(group[i], x_test)
score.append(
caculate_fitness(x_train_tmp, y_train, x_test_tmp, y_test))
group_score = []
for index, score in enumerate(score):
group_score.append([index, score])
#Sort by the score of each subset
group_score = sorted(group_score, key=lambda x: x[1], reverse=True)
"""
__title__ = ''
__author__ = 'WNI10'
__mtime__ = '2018/9/15'
"""
from sklearn.datasets import load_iris
import function
# from sklearn import tree
if __name__ == '__main__':
# iris = load_iris()
# clf = tree.DecisionTreeClassifier()
# clf = clf.fit(iris.data,iris.target)
#
# import graphviz
# dot_data = tree.export_graphviz(clf,out_file=None)
# graph = graphviz.Source(dot_data)
# graph.render("iris")
# data = load_iris().data
# label = load_iris().target
# function.OB(data,label)
###################################
#画出树形图
###################################
data, label = function.load_data("f60-1-3.xlsx", 1)
data, label = function.createdataset(data, label, 0.2, 1, 5)
function.OB(data[0], label[0], 'temp', 5, 50, 100)