from keras.layers.core import Activation from keras.layers import Embedding from keras.layers import Input, Flatten from keras.layers.core import Dropout from keras.layers.core import Dense from keras.callbacks import EarlyStopping from keras.initializers import glorot_normal, glorot_uniform from gensim.models.keyedvectors import KeyedVectors from keras import optimizers from keras.utils import to_categorical from keras import regularizers #Lectura de los datos input_size = 20 print("Leyendo datos de entrenamiento...") data_train, label_train = readData( 'tass_2018_task_4_subtask2_train_dev/SANSE_train-2.tsv', input_size) print(data_train.shape) print(label_train.shape) print("Leyendo datos de desarrollo...") data_dev, label_dev = readData( 'tass_2018_task_4_subtask2_train_dev/SANSE_dev-2.tsv', input_size) print(data_dev.shape) print(label_dev.shape) print("Leyendo datos de test...") data_test_1, id_test_1 = readDataTest('/Users/nuria/SEPLN/test-s2.tsv', input_size)
def load(self): self.data = read_data.readData(self) self.report(self.data.filepath)
def processData(filePath,file_1,train = True): df = readData(filePath,file_1) print("================这是一条分割线=============") df = df.drop(['unnamed: 0'],axis = 1) ## 先连接其他数据 df.drop([ '未结清贷款account_count', '未销户贷记卡account_count', '未结清贷款credit_limit', '未销户贷记卡credit_limit', '未销户贷记卡max_credit_limit_per_org', '未销户贷记卡min_credit_limit_per_org', '未结清贷款balance', '未销户贷记卡used_credit_limit', '未结清贷款latest_6m_used_avg_amount', '未销户贷记卡latest_6m_used_avg_amount', 'changing_amount', 'last_months'],axis = 1,inplace = True) if train: df_temp = pd.read_csv('D:\\workspace python\\contest\\qihuoout.csv') else: df_temp = pd.read_csv('D:\\workspace python\\contest\\out_test.csv') df = pd.merge(df,df_temp,left_on = 'report_id', right_on = 'report_id',how = 'left') del df_temp #df.sort_values(by='y',inplace = True) ## 变量名与变量格式修改 df.drop('id_card',axis = 1,inplace = True) df.drop('loan_date',axis = 1,inplace = True) df.drop('agent',axis = 1,inplace = True) ## 以后再处理了 df.work_province.isnull().sum() ## edu df.edu_level.value_counts() mapping = {'本科':'本科及以上', '硕士研究生':'本科及以上', '博士研究生':'本科及以上', '硕士及以上':'本科及以上', '高中':'专科以下', '初中':'专科以下', '专科及以下':'专科以下', '其他':'专科以下', '专科':'专科'} df.edu_level = df.edu_level.map(mapping) df.edu_level = df.edu_level.fillna('missing') del mapping ## 公积金 df.has_fund = df.has_fund.fillna('missing') ## 婚姻 df.marry_status.value_counts() mapping = {'离婚':'离婚', '离异':'离婚', '丧偶':'其他', '已婚':'已婚', '未婚':'未婚', '其他':'其他'} df.marry_status = df.marry_status.map(mapping) del mapping ## 收入 df.salary.isnull().sum() df.salary = df.salary.fillna('missing') ## y if train: df.y = df.y.astype('category') ''' pd.crosstab(df.y,df.salary).div( pd.crosstab( df.y,df.salary).sum(1).astype(float),axis = 0).plot( kind = 'bar') ''' ####------下一个 df['ln_settle_rate'] = df.贷款结清比例 del df['贷款结清比例'] df['ln_settle_rate'] = groupImmpute(df,'ln_settle_rate') ''' df.boxplot('ln_settle_rate',by = 'y') ''' ## 贷款是否异常 df['ln_abnormal'] = df.贷款是否异常 del df['贷款是否异常'] df.ln_abnormal = df.ln_abnormal.fillna('missing')
# -*- coding: utf-8 -*- """ Created on Mon Nov 16 17:44:11 2015 @author: zc """ from sklearn.externals import joblib # #clf = joblib.load('svmClassifier.pkl') import read_data import numpy as np a=read_data.readData(1,'rbf'); print a #data_set=[1,2,3,4] #kernel=['sig','rbf','poly','linear'] # #accu_matrix=np.ones([4,4]) #for i in range(0,4): # for j in range(0,4): # accu_matrix[i,j]=read_data.readData(data_set[i],kernel[j]) # print data_set[i],kernel[j],accu_matrix[i,j] # ([[ 0.8590604 , 0.8590604 , 0.17785235, 0.8590604 ], # [ 0.8283611 , 0.8407594 , 0.51452925, 0.82874855], # [ 0.72736626, 0.71707819, 0.16049383, 0.72530864], # [ 0.68787328, 0.69047001, 0.34484549, 0.687873 ]])
client = airsim.VehicleClient() client.confirmConnection() # Camera Information camera = client.simGetCameraInfo("3") test_camera = client.simGetCameraInfo("1") if (test_camera.pose != down): client.simSetCameraOrientation("1", down) client.simSetCameraOrientation("2", down) FoV = 90 # Coordinate transformation enu_2_ned = utils.qnorm(airsim.Quaternionr(0.7071068, 0.7071068, 0, 0), 10) # panda read csv position, attitude, accelerometer, gyroscope, noisy_accelerometer, noisy_gyroscope, time = traj.readData( '/home/tigerteam/gnss-ins-sim/demo_saved_data/openIMU_landing/') # Get position and attitude data from panda read ned_position_data = traj.getPosition(position) ned_quaternion_data = traj.getAttitude(attitude) time_new = traj.getTime(time) # Gate for including simulated IMU data or perfect IMU readings if (TRUTH_IMU): print("Perfect IMU Data Selected") ned_accel = traj.getAccel(accelerometer) ned_gyro = traj.getGyro(gyroscope) else: print("Noisy IMU Data Selected") ned_accel = traj.getNoisyAccel(noisy_accelerometer) ned_gyro = traj.getNoisyGyro(noisy_gyroscope)
def importFile(self): #import UI execute #data_path = ui df = read_data.readData()
def runMeta(book, sentences, wsent, char_list, job_labels, gender_label, job=False, gender=False, sentiment=False): """ Compute various metadata about characters in char_list :param sentences: list(dict) List of dicts. Each dict is a sentence and contains 'nostop', 'words', 'tags' :param wsetn: dictionary of sentences by character :param char_list: list(unicode) List of character names in unicode Compound names are concatenated as in sentences :param job_labels: dict of character -> [job label] """ ### GLOBAL PARAMS # classifier_data_dict has keys [u'tromper', u'nutrition', u'\xe9motions', u'dormir', u'raison', u'\xe9tats', u'vouloir', u'tuer', u'gu\xe9rir', u'relations', u'm\xe9tiers', u'salutations', u'soupir', u'pens\xe9e', u'parole', u'foi'] classifier_data_dict = readData() sents_by_char = wsent word2vec_model = wordSimilarity.MyModel() char_list = list(reversed(char_list)) # by decreasing mention count save_path = 'metadata/' + book + '_' ################ JOBS ################# # Define parameters job_list = classifier_data_dict[u'm\xe9tiers'] N_CHARS = 10 # Num of chars to compute scores for -> default all predictors = ['count', 'proximity'] if job: # Compute predictions df_job_full_const = jobPredictor(sentences, wsent, char_list, job_labels, job_list, word2vec_model, decreasing=False, full=True) df_job_full_decr = jobPredictor(sentences, wsent, char_list, job_labels, job_list, word2vec_model, decreasing=True, full=True) df_job_expo_const = jobPredictor(sentences, wsent, char_list, job_labels, job_list, word2vec_model, decreasing=False, full=False) df_job_expo_decr = jobPredictor(sentences, wsent, char_list, job_labels, job_list, word2vec_model, decreasing=True, full=False) # Save to csv df_job_full_const.to_csv(save_path + 'job_full_const.csv', encoding='utf-8') df_job_full_decr.to_csv(save_path + 'job_full_decr.csv', encoding='utf-8') df_job_expo_decr.to_csv(save_path + 'job_expo_decr.csv', encoding='utf-8') df_job_expo_const.to_csv(save_path + 'job_expo_const.csv', encoding='utf-8') ################## GENDER ################### # Load gender dict if gender: # Compute predictions gender_nosolo = genderPredictor(book, sentences, sents_by_char, char_list, gender_label, full=True, solo=False) gender_solo = genderPredictor(book, sentences, sents_by_char, char_list, gender_label, full=True, solo=True) gender_nosolo_w = genderPredictor(book, sentences, sents_by_char, char_list, gender_label, full=True, solo=False, weighted=True) gender_solo_w = genderPredictor(book, sentences, sents_by_char, char_list, gender_label, full=True, solo=True, weighted=True) # Save to csv gender_nosolo.to_csv(save_path + 'gender_nosolo.csv', encoding='utf-8') gender_solo.to_csv(save_path + 'gender_solo.csv', encoding='utf-8') gender_nosolo_w.to_csv(save_path + 'gender_nosolo_w.csv', encoding='utf-8') gender_solo_w.to_csv(save_path + 'gender_solo_w.csv', encoding='utf-8') if sentiment: # # Compute predictions sentiment_nosolo = sentimentPredictor(sentences, sents_by_char, char_list, reduced=False) sentiment_nosolo.to_csv(save_path + 'sentiment_nosolo_top.csv', encoding='utf-8') # sentiment_solo = sentimentPredictor(sentences, sents_by_char, char_list, reduced=False, solo=True) # sentiment_solo.to_csv(save_path + 'sentiment_solo_top.csv', encoding='utf-8') # sentimentPredictor(book, sentences, sents_by_char, char_list, reduced=False, write=True) # Print stats tokens = 0 job_len = len([item for item in job_labels.values() if item]) job_tok = len( [item for sublist in job_labels.values() for item in sublist]) gender_len = len([item for item in gender_label.values() if item != '-']) for s in sentences: tokens += len(s['words']) print('{}, {}, {}, ({}, {}), {}'.format(book, tokens, len(char_list), job_len, job_tok, gender_len))
keepProb = keepProb = np.zeros_like(out_layer) keepProb[np.arange(self.train_number), self.input_label] = 1.0 for i in range(fb_numbers): self.output_weight += -np.dot(self.hidden_layer[-1].T, out_layer - keepProb) / self.train_number # pre_tidu=1 # if self.layer_numbers>3: # pre_tidu*=np.dot(keepProb - out_layer,self.output_weight.T)*self.sigmoidDaoShu(self.hidden_layer[-1]) #表达式中的wji和之前的一大堆相乘 # self.weights_hidden[-1] += -np.dot(self.hidden_layer[-2].T, pre_tidu) # # pre_sigema= # pre_tidu = keepProb - out_layer pre_weight = self.output_weight for i in range(0, self.layer_numbers - 3): #隐藏层中的梯度表达式,以及隐藏层到输出层的表达式 pre_tidu = np.dot(pre_tidu, pre_weight.T) * self.sigmoidDaoShu( self.hidden_layer[-i - 1]), self.weights_hidden[-1 - i] += -np.dot( self.hidden_layer[-2 - i].T, pre_tidu) pre_weight = self.weights_hidden[-1 - i] # pre_weight=self.weights_hidden[-1-i] #隐藏层到输出层的表达式 # pre_tidu = np.dot(pre_tidu, self.weights1.T) * self.sigmoidDaoShu(self.hidden_layer[1]), # self.weights1 += -np.dot(self.hidden_layer[0].T, pre_tidu) return if __name__ == "__main__": train_obj = read_data.readData() train_data, train_label = read_data.read_picture_data(True)