def arma_ex(term='first'):
prp = PreProcessor(term) # 数据管理器
preMapping = get_testroad_adjoin(prp)
for pre_id in tqdm.tqdm(preMapping.keys()):
instand_id = preMapping[pre_id]
try:
pred_pre = predict(prp.get_roadflow_by_road(instand_id))
except Exception as e:
print(instand_id, end='\t')
print(e)
continue
pred_pre.to_frame()
pred_pre = pred_pre.dropna(axis=0, how="any")
for i in range(len(pred_pre)):
pred_pre.iloc[[i]] = int(pred_pre.iloc[[i]])
pred = pd.DataFrame(pred_pre.values, columns=['value'])
pred['timestamp'] = pred_pre.index
pred['date'] = pred['timestamp'].apply(lambda x: x.strftime('%d'))
pred['timeBegin'] = pred['timestamp'].apply(
lambda x: x.strftime('%H:%M'))
pred['crossroadID'] = instand_id
pred['min_time'] = pred['timestamp'].apply(
lambda x: int(x.strftime('%M')))
pred = pred[pred['min_time'] >= 30]
pred.drop(['timestamp'], axis=1, inplace=True)
order = ['date', 'crossroadID', 'timeBegin', 'value']
pred = pred[order]
pred.to_csv(r'data\tmp\{}\pred_{}.csv'.format(term, pre_id),
index=False,
columns=['date', 'crossroadID', 'timeBegin', 'value'])
def plot_roadflow():
# ******载入数据******
day = 3
prp = PreProcessor() # 数据管理器
dfFlow, dFlow = prp.get_roadflow(day) # 原始车流数据表，车流量时序数据
# *****绘图示例******
key = list(dFlow.keys())[0]
seFolw = dFlow[key]
seFolw.plot()
plt.title(f'{day}号交通口{key}车流量时序图')
plt.ylabel('车流量/5min')
plt.xlabel('时间/t')
plt.show()
def regression_ex(term='final'):
keylst = [
100115, 100245, 100246, 100374, 100003, 100004, 100020, 100285, 100159,
100287, 100288, 100164, 100300, 100179, 100053, 100183, 100315, 100061,
100193, 100066, 100457, 100343, 100217, 100434, 100249, 100316, 100329,
100019, 100340, 100041, 100069
]
keylst = [val for val in keylst for i in range(3024)]
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
prp = PreProcessor(term) # 数据管理器
train_x, train_y, test_x = prp.load_traindata()
# 训练模型
lr = LinearRegression()
# print(train_x.iloc[:, 0:1])
lr.fit(train_x.iloc[:, 0:1].values, train_y)
test_y = lr.predict(test_x.values)
# print(test_y)
return test_y
def test_hmm_all(): """ This method tests the entire workflow: PreProcessor: populate the label codebook, feature codebook, and instance list from the dataset """ # Please specify the dataset path here train_set_path = "C:\\Users\\DIAOSHUO\\Dropbox\\SNLP\\cs134assn2\\np_chunking_wsj_15_18_train" test_set_path = "C:\\Users\\DIAOSHUO\\Dropbox\\SNLP\\cs134assn2\\np_chunking_wsj_20_test" # Preprocess pp = PreProcessor()#use hmm = HMM() hmm.label_codebook= pp.get_label_codebook() hmm.feature_codebook = pp.get_feature_codebook() #train_set = pp.make_instance_list() # default, the dataset path is the training set, np_chunking_wsj_15_18_train #test_set = pp.make_instance_list(test_set_path) train_instance_list = pp.get_instance_list(train_set_path) test_instance_list = pp.get_instance_list(test_set_path) #running 3 kinds of test split_train_test(hmm, train_instance_list, [0.8,0.2]) n_fold_cross_validation(hmm,train_instance_list) simple_train_test(hmm,train_instance_list, test_instance_list)
def test_hmm(self): pp = PreProcessor() pp.test_preprocess() instance_list = pp.get_instance_list() self.label_codebook=pp.get_label_codebook() self.feature_codebook=pp.get_feature_codebook() self.train(instance_list) print "\ntransition_count_table--------------------" print self.transition_count_table print "\ntransition_matrix-------------------------" print self.transition_matrix print "\ninitial_state_count_table------------------" print self.initial_state_count_table print "\ntermination_state_count_table------------------" print self.termination_state_count_table print "\nemission matrix----------------------------" print self.emission_matrix for i in range(10): self.test_classify_instance(instance_list[i])
100193, 100066, 100457, 100343, 100217, 100434, 100249, 100316, 100329,
100019, 100340, 100041, 100069
]
keylst = [val for val in keylst for i in range(3024)]
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
prp = PreProcessor(term) # 数据管理器
train_x, train_y, test_x = prp.load_traindata()
# 训练模型
lr = LinearRegression()
# print(train_x.iloc[:, 0:1])
lr.fit(train_x.iloc[:, 0:1].values, train_y)
test_y = lr.predict(test_x.values)
# print(test_y)
return test_y
if __name__ == '__main__':
term = 'final' # 初赛:first；复赛：final
# term = 'first' # 初赛:first；复赛：final
prp = PreProcessor(term) # 数据管理器
# train_x, train_y, test_x = prp.load_traindata()
# arma_ex(term) # 时序模型
fe = FeatureEn(prp)
# fe.get_train_data()
# keylst = fe.get_text_data()
# print(keylst)
# ap(fe)
regression_ex(term)
import os os.environ['CUDA_DIVICE_ORDER'] = 'PCI_BUS_ID' os.environ['CUDA_VISIBLE_DEVICES'] = '1' from pre_process import PreProcessor wav_dir = './NSynth' A_dist_list = [] A = PreProcessor() A.experiment_A(wav_dir=wav_dir) A.get_dist_meanstd(dist_list=A_dist_list) B_dist_list = [] B = PreProcessor() B.experiment_B(wav_dir=wav_dir) B.get_dist_meanstd(dist_list=B_dist_list)