By: 顾 瞻 GU Zhan (Sam)
July 2017
In [1]:
# from __future__ import print_function, division
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import pandas as pd
import operator
from scipy import interp
from itertools import cycle
from sklearn import svm
from sklearn.utils.validation import check_random_state
from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import AdaBoostRegressor
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.ensemble import BaggingRegressor
from sklearn.linear_model import LinearRegression
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import BaggingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import roc_curve, auc
from statsmodels.graphics.mosaicplot import mosaic
print(__doc__)
In [2]:
df_history_ts = pd.read_csv('data/history_ts.csv')
df_history_ts_process = df_history_ts.copy()
df_history_ts_process.tail()
Out[2]:
In [3]:
df_history_table = pd.read_csv('data/history_table.csv')
df_history_table_process = df_history_table.copy()
df_history_table_process.tail()
Out[3]:
In [4]:
parm_ts_cycle = 61 # seconds/records per month
print('parm_ts_cycle : %d seconds' % parm_ts_cycle)
parm_ts_month = int(len(df_history_ts) / parm_ts_cycle)
print('parm_ts_month : %d months' % parm_ts_month)
parm_calculate_base_price_second = 15 # Use the current month's bid-price as base-price at this seconds. Later to derive increment-price
parm_calculate_prev_bp = 15 # Number of previous price/increment to include, i.e. previous 2sec, 3sec, 4sec, 5sec ... 15sec
parm_calculate_mv = 15 # Number of previous price/increment Moving Average to calculate, i.e. previous 2sec, 3sec, 4sec, 5sec ... 15sec
parm_calculate_target_second = 7 # How many seconds in future to predict: target variable
parm_calculate_prev_month = 3 # Number of previous month to include (need to remove earliest x month from training data)
parm_record_cut_row_head = max(parm_calculate_base_price_second, parm_calculate_prev_bp, parm_calculate_mv)
parm_record_cut_row_tail = parm_calculate_target_second
parm_record_cut_month_head = parm_calculate_prev_month + 1
parm_ts_valid_cycle = parm_ts_cycle - parm_record_cut_row_head - parm_record_cut_row_tail
print('parm_ts_valid_cycle : %d seconds' % parm_ts_valid_cycle)
parm_ts_valid_month = parm_ts_month - parm_record_cut_month_head
print('parm_ts_valid_month : %d months' % parm_ts_valid_month)
if parm_record_cut_month_head < 10:
parm_record_cut_ccyy = pd.to_datetime('2015-0'+str(parm_record_cut_month_head))
else:
parm_record_cut_ccyy = pd.to_datetime('2015-'+str(parm_record_cut_month_head))
print('parm_record_cut_ccyy : %s' % parm_record_cut_ccyy)
print('parm_record_cut_month_head : %d months' % parm_record_cut_month_head)
print('parm_record_cut_row_head : %d seconds' % parm_record_cut_row_head)
print('parm_record_cut_row_tail : %d seconds' % parm_record_cut_row_tail)
print(' : ' )
print(' : ' )
print(' : ' )
In [5]:
df_history_ts_process.head()
Out[5]:
In [ ]:
In [6]:
# date of current month
df_history_ts_process['date-curr'] = df_history_ts_process.apply(lambda row: pd.to_datetime(row['ccyy-mm']), axis=1)
# date of previous month
df_history_ts_process['date-prev'] = df_history_ts_process.apply(lambda row: row['date-curr'] - pd.offsets.MonthBegin(1), axis=1)
# Year
df_history_ts_process['year'] = df_history_ts_process.apply(lambda row: row['ccyy-mm'][0:4], axis=1)
# Month
df_history_ts_process['month'] = df_history_ts_process.apply(lambda row: row['ccyy-mm'][5:7], axis=1)
# Hour
df_history_ts_process['hour'] = df_history_ts_process.apply(lambda row: row['time'][0:2], axis=1)
# Minute
df_history_ts_process['minute'] = df_history_ts_process.apply(lambda row: row['time'][3:5], axis=1)
# Second
df_history_ts_process['second'] = df_history_ts_process.apply(lambda row: row['time'][6:8], axis=1)
In [9]:
# df_history_ts_process
# df_history_ts_process[1768:]
In [10]:
# new ['base-price']
gap = 1 # only one new feature/column
for gap in range(1, gap+1):
col_name = 'base-price'+str(parm_calculate_base_price_second)+'sec'
col_name_base_price = col_name
col_data = pd.DataFrame(columns=[col_name])
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
for i in range(0, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['bid-price'][month*parm_ts_cycle+parm_calculate_base_price_second]
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [11]:
# df_history_ts_process
# df_history_ts_process[1768:]
In [12]:
# new ['increment-price'] = ['bid-price'] - ['base-price']
df_history_ts_process['increment-price'] = df_history_ts_process.apply(lambda row: row['bid-price'] - row[col_name_base_price], axis=1)
In [13]:
# df_history_ts_process
# df_history_ts_process[1768:]
In [14]:
plt.figure()
plt.plot(df_history_ts_process['bid-price'])
plt.plot(df_history_ts_process[col_name_base_price])
plt.plot()
plt.figure()
plt.plot(df_history_ts_process['increment-price'])
plt.plot()
Out[14]:
In [15]:
# previous N sec ['increment-price-target']
for gap in range(1, 2):
col_name = 'increment-price-target'
col_data = pd.DataFrame(columns=[col_name])
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
for i in range(0, (parm_ts_cycle - parm_calculate_target_second)):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['increment-price'][month*parm_ts_cycle+i+parm_calculate_target_second]
for i in range((parm_ts_cycle - parm_calculate_target_second), parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = 0
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [16]:
plt.figure()
plt.plot(df_history_ts_process['increment-price'])
plt.plot(df_history_ts_process['increment-price-target'])
plt.plot()
plt.figure()
plt.plot(df_history_ts_process['increment-price'][1768:])
plt.plot(df_history_ts_process['increment-price-target'][1768:])
plt.plot()
Out[16]:
In [ ]:
In [17]:
# previous 'parm_calculate_prev_bp' sec ['increment-price']
gap = parm_calculate_prev_bp
for gap in range(1, gap+1):
col_name = 'increment-price-prev'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
# col_data_zeros = pd.DataFrame({col_name: np.zeros(gap)})
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
# col_data.append(col_data_zeros)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['increment-price'][month*parm_ts_cycle+i-gap]
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [18]:
# previous 'parm_calculate_mv' sec Moving Average ['increment-price']
gap = parm_calculate_mv
for gap in range(2, gap+1): # MV starts from 2 seconds, till parm_calculate_mv
col_name = 'increment-price-mv'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = \
np.mean(df_history_ts_process['increment-price'][month*parm_ts_cycle+i-gap:month*parm_ts_cycle+i])
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [ ]:
# df_history_ts_process[1768:]
In [19]:
plt.figure()
plt.plot(df_history_ts_process['increment-price'][1768:])
plt.plot(df_history_ts_process['increment-price-prev3sec'][1768:])
plt.plot(df_history_ts_process['increment-price-prev7sec'][1768:])
plt.plot(df_history_ts_process['increment-price-prev11sec'][1768:])
plt.plot(df_history_ts_process['increment-price-prev15sec'][1768:])
plt.plot()
Out[19]:
In [20]:
plt.figure()
plt.plot(df_history_ts_process['increment-price'][1768:])
plt.plot(df_history_ts_process['increment-price-mv3sec'][1768:])
plt.plot(df_history_ts_process['increment-price-mv7sec'][1768:])
plt.plot(df_history_ts_process['increment-price-mv11sec'][1768:])
plt.plot(df_history_ts_process['increment-price-mv15sec'][1768:])
plt.plot()
Out[20]:
In [ ]:
In [21]:
df_history_table_process.tail()
Out[21]:
In [22]:
# date of current month
df_history_table_process['date-curr'] = df_history_table_process.apply(lambda row: pd.to_datetime(row['ccyy-mm']), axis=1)
df_history_table_process['d-avg-low-price'] = df_history_table_process.apply(lambda row: row['deal-price-avg'] - row['deal-price-low'], axis=1)
df_history_table_process['ratio-bid'] = df_history_table_process.apply(lambda row: row['volume-plate'] / row['volume-bidder'], axis=1)
In [23]:
df_history_ts_process = pd.merge(df_history_ts_process, df_history_table_process[['date-curr', 'volume-plate', 'ratio-bid']], how = 'left', left_on = 'date-curr', right_on = 'date-curr')
In [24]:
df_history_ts_process = pd.merge(df_history_ts_process, df_history_table_process[['date-curr', 'volume-plate', 'ratio-bid', 'deal-early-second', 'deal-price-avg']], how = 'left', left_on = 'date-prev', right_on = 'date-curr')
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [26]:
df_history_ts_process.columns
Out[26]:
In [27]:
# housekeeping: delete some columns
df_history_ts_process.drop('date-curr_y', axis=1, inplace=True)
In [28]:
# remove first 'parm_record_cut_ccyy' months from dataset
df_history_ts_process = df_history_ts_process[df_history_ts_process['date-curr_x'] > parm_record_cut_ccyy]
df_history_ts_process = df_history_ts_process[df_history_ts_process['date-prev'] > parm_record_cut_ccyy]
In [29]:
# total 61 seconds/rows per month:
# remove first 'parm_record_cut_row_head' reconds
# remove last 'parm_record_cut_row_tail' reconds
df_history_ts_process = df_history_ts_process[df_history_ts_process['second'] >= str(parm_record_cut_row_head) ]
df_history_ts_process = df_history_ts_process[df_history_ts_process['second'] <= str(60 - parm_record_cut_row_tail) ]
# df_history_ts_process = df_history_ts_process[df_history_ts_process['second'] > parm_record_cut_row_head ]
In [30]:
# Reset index after housekeeping
df_history_ts_process = df_history_ts_process.reset_index(drop=True)
In [32]:
df_history_ts_process.tail()
Out[32]:
In [31]:
plt.figure()
plt.plot(df_history_ts_process['increment-price'][974:])
plt.plot(df_history_ts_process['increment-price-mv3sec'][974:])
plt.plot(df_history_ts_process['increment-price-mv7sec'][974:])
plt.plot(df_history_ts_process['increment-price-mv11sec'][974:])
plt.plot(df_history_ts_process['increment-price-mv15sec'][974:])
plt.plot()
Out[31]:
In [ ]:
In [33]:
df_history_ts_process.head()
Out[33]:
In [35]:
X = df_history_ts_process[[
# 'ccyy-mm', 'time', 'bid-price', 'date-curr_x', 'date-prev', 'year',
'month',
# 'hour', 'minute',
'second', 'base-price15sec',
'increment-price',
# 'increment-price-target',
'increment-price-prev1sec',
'increment-price-prev2sec', 'increment-price-prev3sec',
'increment-price-prev4sec', 'increment-price-prev5sec',
'increment-price-prev6sec', 'increment-price-prev7sec',
'increment-price-prev8sec', 'increment-price-prev9sec',
'increment-price-prev10sec', 'increment-price-prev11sec',
'increment-price-prev12sec', 'increment-price-prev13sec',
'increment-price-prev14sec', 'increment-price-prev15sec',
'increment-price-mv2sec', 'increment-price-mv3sec',
'increment-price-mv4sec', 'increment-price-mv5sec',
'increment-price-mv6sec', 'increment-price-mv7sec',
'increment-price-mv8sec', 'increment-price-mv9sec',
'increment-price-mv10sec', 'increment-price-mv11sec',
'increment-price-mv12sec', 'increment-price-mv13sec',
'increment-price-mv14sec', 'increment-price-mv15sec', 'volume-plate_x',
'ratio-bid_x', 'volume-plate_y', 'ratio-bid_y', 'deal-early-second',
'deal-price-avg', 'deal-price-avg'
]]
X_col = X.columns # get the column list
# X = StandardScaler().fit_transform(X.as_matrix())
X = X.as_matrix()
# y = StandardScaler().fit_transform(df_wnv_raw[['increment-price-target']].as_matrix()).reshape(len(df_wnv_raw),)
y = df_history_ts_process[['increment-price-target']].as_matrix().reshape(len(df_history_ts_process),)
In [36]:
X_col
Out[36]:
In [39]:
plt.figure()
plt.plot(X)
plt.figure()
plt.plot(y)
Out[39]:
In [ ]:
In [40]:
rng = check_random_state(0)
In [41]:
# GB
classifier_GB = GradientBoostingRegressor(n_estimators=1500, # score: 0.94608 (AUC 0.81419), learning_rate=0.001, max_features=8 <<< Best
# loss='deviance',
# subsample=1,
# max_depth=5,
# min_samples_split=20,
learning_rate=0.002,
# max_features=10,
random_state=rng)
In [42]:
# AB
classifier_AB = AdaBoostRegressor(n_estimators=1500, # score: 0.93948 (AUC 0.88339), learning_rate=0.004 <<< Best
learning_rate=0.002,
random_state=rng)
In [43]:
# RF
classifier_RF = RandomForestRegressor(n_estimators=1500, # score: 0.94207 (AUC 0.81870), max_depth=3, min_samples_split=20, <<< Best
# max_features=10,
# max_depth=3,
# min_samples_split=20,
random_state=rng)
In [44]:
# ET
classifier_ET = ExtraTreesRegressor(n_estimators=1000, # score: 0.94655 (AUC 0.84364), max_depth=3, min_samples_split=20, max_features=10 <<< Best
# max_depth=3,
# min_samples_split=20,
# max_features=10,
random_state=rng)
In [45]:
# BG
classifier_BG = BaggingRegressor(n_estimators=500, # score: 0.70725 (AUC 0.63729) <<< Best
# max_features=10,
random_state=rng)
In [46]:
classifier_LR = LinearRegression() # score: 0.90199 (AUC 0.80569)
In [47]:
# classifier_SVCL = svm.SVC(kernel='linear', probability=True, random_state=rng) # score: 0.89976 (AUC 0.70524)
classifier_SVRL = svm.SVR() # score: 0.89976 (AUC 0.70524)
In [48]:
classifier_SVRR = svm.SVR(kernel='rbf') # score: 0.80188 (AUC 0.50050)
# classifier_SVRR = svm.SVR(kernel='poly') # score: 0.80188 (AUC 0.50050)
In [49]:
classifier_KNN = KNeighborsRegressor(n_neighbors=2) # score: 0.94018 (AUC 0.72792)
cv = cross_val_score(classifier_KNN,
X,
y,
cv=StratifiedKFold(parm_ts_valid_month))
print('KNN CV score: {0:.5f}'.format(cv.mean()))
In [ ]:
In [50]:
# classifier = classifier_GB # 324.632308296
classifier = classifier_AB # 429.646733221
# classifier = classifier_RF # 175.504322802
# classifier = classifier_ET # 172.097916817, 0.0724812030075
# classifier = classifier_BG # 175.451381872
# classifier = classifier_LR # 128.465059749, 0.11
# classifier = classifier_SVRL # 3789.82169312
# classifier = classifier_SVRR # 3789.82169312, 0.10754224349
In [51]:
n_splits = parm_ts_valid_cycle
print(n_splits)
# n_splits=54 # 19 seconds/records for each bidding month
# n_splits=19 # 19 seconds/records for each bidding month
n_fold = parm_ts_valid_month
print(n_fold)
# X_train_1 = X[0:(len(X)-batch*n_splits)]
# y_train_1 = y[0:(len(X)-batch*n_splits)]
# X_test_1 = X[(len(X)-batch*n_splits):((len(X)-batch*n_splits)+n_splits)]
# y_test_1 = y[(len(X)-batch*n_splits):((len(X)-batch*n_splits)+n_splits)]
In [52]:
n_fold=5
In [54]:
y_pred = {}
y_test = {}
y_pred_org = {}
y_test_org = {}
i = 0
for batch in range(1, n_fold):
X_train_1 = X[0:(len(X)-batch*n_splits)]
y_train_1 = y[0:(len(X)-batch*n_splits)]
X_test_1 = X[(len(X)-batch*n_splits):((len(X)-batch*n_splits)+n_splits)]
y_test_1 = y[(len(X)-batch*n_splits):((len(X)-batch*n_splits)+n_splits)]
print(len(X_train_1))
# ReScale
ScalerX = StandardScaler()
ScalerX.fit(X_train_1)
X_train_1 = ScalerX.transform(X_train_1)
X_test_1 = ScalerX.transform(X_test_1)
ScalerY = StandardScaler()
ScalerY.fit(y_train_1.reshape(-1, 1))
y_train_1 = ScalerY.transform(y_train_1.reshape(-1, 1))
y_test_1 = ScalerY.transform(y_test_1.reshape(-1, 1))
y_pred[i] = classifier.fit(X_train_1, y_train_1).predict(X_test_1)
y_test[i] = y_test_1
y_pred_org[i] = ScalerY.inverse_transform(y_pred[i])
y_test_org[i] = ScalerY.inverse_transform(y_test[i])
plt.figure()
plt.plot(y_train_1)
plt.plot()
plt.figure()
plt.plot(y_test[i])
plt.plot(y_pred[i])
plt.plot()
i += 1
In [55]:
k = []
for i in range(0, len(y_test)):
k.append(np.mean(np.sqrt(np.square(y_test[i] - y_pred[i]))))
k_mean = np.mean(k)
print(k_mean)
print()
print(k)
In [56]:
k = []
for i in range(0, len(y_test)):
k.append(np.mean(np.sqrt(np.square(y_test[i][35:37] - y_pred[i][35:37]))))
k_mean = np.mean(k)
print(k_mean)
print()
print(k)
In [57]:
k = []
for i in range(0, len(y_test)):
k.append(np.mean(np.sqrt(np.square(y_test_org[i] - y_pred_org[i]))))
k_mean = np.mean(k)
print(k_mean)
print()
print(k)
In [62]:
k = []
for i in range(0, len(y_test)):
k.append(np.mean(np.sqrt(np.square(y_test_org[i][35:37] - y_pred_org[i][35:37]))))
k_mean = np.mean(k)
print(k_mean)
print()
print(k)
In [69]:
# 50 second predicts 57 second
k = []
for i in range(0, len(y_test)):
k.append(np.mean(np.sqrt(np.square(y_test_org[i][35:36] - y_pred_org[i][35:36]))))
k_mean = np.mean(k)
print(k_mean)
print()
print(k)
In [70]:
plt.plot(y_test_org[0])
plt.plot(y_pred_org[0])
Out[70]:
In [71]:
plt.plot(k)
Out[71]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
y_test[1][13:]
In [ ]:
y_pred[1][13:]
In [ ]:
np.mean(np.sqrt(np.square(y_test[4] - y_pred[4])))
In [ ]:
np.mean(np.sqrt(np.square(y_test[4][13:16] - y_pred[4][13:16])))
In [ ]:
In [ ]:
y_pred_df = pd.DataFrame.from_dict(y_pred)
In [ ]:
y_pred_df.columns=['month 7','month 6','month 5','month 4','month 3','month 2','month 1']
In [ ]:
y_pred_df.to_csv('bid_results_v001.csv', index=False)
In [ ]:
y_pred_df
In [ ]:
In [ ]:
# previous N sec ['bid-price']
gap = parm_calculate_prev_bp
for gap in range(1, gap+1):
col_name = 'bid-price-prev'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
col_data_zeros = pd.DataFrame({col_name: np.zeros(gap)})
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
col_data.append(col_data_zeros)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['bid-price'][month*parm_ts_cycle+i-gap]
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [ ]:
# previous 2 sec Moving Average ['bid-price']
gap = parm_calculate_mv
for gap in range(2, gap+1): # MV starts from 2 seconds, till parm_calculate_mv
col_name = 'bid-price-mv'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
col_data_zeros = pd.DataFrame({col_name: np.zeros(gap)})
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
col_data.append(col_data_zeros)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = \
np.mean(df_history_ts_process['bid-price'][month*parm_ts_cycle+i-gap:month*parm_ts_cycle+i])
df_history_ts_process[col_name] = col_data
print('Total records processed : ', len(col_data))
In [ ]:
df_history_ts_process[1768:]
In [ ]:
In [ ]:
In [ ]:
In [ ]:
# previous 2 sec Moving Average ['bid-price']
gap = parm_calculate_mv
for gap in range(1, gap+1):
col_name = 'bid-price-mv'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
print('Creating : ', col_name)
for month in range(0, parm_ts_month):
# print('month : ', month)
col_data.append(col_data_zeros)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['bid-price'][month*parm_ts_cycle+i-gap]
df_history_ts_process[col_name] = col_data
print('len : ', len(col_data))
In [ ]:
In [ ]:
In [ ]:
# previous N sec
gap = 1
gap = 2
gap = 3
gap = 4
gap = 5
gap = 6
gap = 7
gap = 8
gap = 9
gap = 10
col_name = 'bid-price-prev'+str(gap)+'sec'
col_data = pd.DataFrame(columns=[col_name])
for month in range(0, parm_ts_month):
# print('month : ', month)
col_data.append(col_data_zeros)
for i in range(0, gap):
col_data.loc[month*parm_ts_cycle+i] = 0
for i in range(gap, parm_ts_cycle):
col_data.loc[month*parm_ts_cycle+i] = df_history_ts_process['bid-price'][month*parm_ts_cycle+i]
print('len : ', len(col_data))
df_history_ts_process[col_name] = col_data
In [ ]:
len(col_data)
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
# previous 1 sec
gap = 10
col_data = pd.DataFrame({'bid-price-prev'+str(gap)+'sec': np.zeros(gap)})
# for i in range(gap, len(df_history_ts)-1768):
for i in range(gap, parm_ts_cycle):
# print(df_history_ts['bid-price'][i])
col_data.loc[i] = df_history_ts['bid-price'][i]
print(len(col_data))
In [ ]:
In [ ]:
df_history_ts_process = df_history_ts.copy()
In [ ]:
df_history_table_process['tmp'] = col_data['bid-price-prev'+str(gap)+'sec']
In [ ]:
df_history_table_process.tail()
In [ ]:
In [ ]:
In [ ]:
col_data
In [ ]:
In [ ]:
In [ ]: