def iter_over_groups(data, group,features, key): row_num = 0 for x in group: if row_num == 0: data_1 = data[data[key]==x] for i in features: data_1['avg_10' + i.lower() + '_'+ key[0].lower()] = pd.rolling_mean(data_1[i], 7).shift(+1) data_1['sum_15' + i.lower() + '_'+ key[0].lower()] = pd.rolling_mean(data_1[i], 10).shift(+1) data_1['avg_3' + i.lower() + '_'+ key[0].lower()] = pd.rolling_mean(data_1[i], 3).shift(+1) data_1['expand' + i.lower() + '_'+ key[0].lower()] = pd.expanding_mean(data_1[i]).shift(+1) data_1['expand_sum' + i.lower() + '_'+ key[0].lower()] = pd.expanding_sum(data_1[i]).shift(+1) else: data_2 = data[data[key]==x] for i in features: data_2['avg_10' + i.lower() + '_' + key[0].lower()] = pd.rolling_mean(data_2[i], 7).shift(+1) data_2['sum_15' + i.lower() + '_' + key[0].lower()] = pd.rolling_mean(data_2[i], 10).shift(+1) data_2['avg_3' + i.lower() + '_' + key[0].lower()] = pd.rolling_mean(data_2[i],3).shift(+1) data_2['expand' + i.lower() + '_'+ key[0].lower()] = pd.expanding_mean(data_1[i]).shift(+1) data_2['expand_sum' + i.lower() + '_'+ key[0].lower()] = pd.expanding_sum(data_1[i]).shift(+1) data_1 = data_1.append(data_2, ignore_index = True) row_num += 1 return data_1
def analyse(self):
# Logger.log(logging.INFO, "Analyse Strategy", {"scope":__name__, "Rule 1":self._rule1, "Rule 2":self._rule2, "Rule 3":self._rule3, "Type":self._type})
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
query = self.analyseStrategySql % (self._rule1, self._rule2, self._rule3, self._exit, self._type)
self._strategyData = read_sql_query(query, connection, 'Date')
self._strategyData['ExitValueAfterCosts'] = self._strategyData['ExitValue'] - 0.2
connection.close()
exitValueDataFrame = self._strategyData.ix[:,'ExitValueAfterCosts']
mean = exitValueDataFrame.mean()
median = exitValueDataFrame.median()
sum = exitValueDataFrame.sum()
count = exitValueDataFrame.count()
tradesPerYear = count / 10
sharpeRatio = sqrt(tradesPerYear) * exitValueDataFrame.mean() / exitValueDataFrame.std()
self._strategyData["Sum"] = expanding_sum(exitValueDataFrame)
self._strategyData["Max"] = expanding_max(self._strategyData["Sum"])
self._strategyData["Min"] = expanding_min(self._strategyData["Sum"])
self._strategyData["DD"] = self._strategyData["Max"] - self._strategyData["Min"]
runningSum = expanding_sum(exitValueDataFrame)
max2here = expanding_max(runningSum)
dd2here = runningSum - max2here
drawDown = dd2here.min()
Logger.log(logging.INFO, "Analysing Strategy", {"scope":__name__, "Rule 1":self._rule1, "Rule 2":self._rule2, "Rule 3":self._rule3, "Exit":self._exit, "Type":self._type, "Mean":str(mean), "Median":str(median), "Sum":str(sum), "Count":str(count), "SharpeRatio":str(sharpeRatio), "DrawDown":str(drawDown)})
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
c = connection.cursor()
deleteSql = self.deleteStrategySql % (pyswing.globals.pySwingStrategy, self._rule1, self._rule2, self._rule3, self._exit, self._type)
c.executescript(deleteSql)
connection.commit()
insertSql = self.insertStrategySql % (pyswing.globals.pySwingStrategy, self._rule1, self._rule2, self._rule3, self._exit, self._type, str(mean), str(median), str(sum), str(count), str(sharpeRatio), str(drawDown))
c.executescript(insertSql)
connection.commit()
c.close()
connection.close()
def all_dd(df):
df.reset_index(level=0, inplace=True)
df['start'] = pd.NaT; df['end'] = pd.NaT; df['valley'] = pd.NaT; df['length_of_dd'] = np.nan; df['dd'] = np.nan; df['max_dd'] = np.nan
for x in df.index[2:]:
test = df.ix[x-1:x, 'indd']
if (test.notnull()[x] and test.isnull()[x-1]):
df.ix[x,'start'] = df.ix[x, 'Date']
if (test.notnull()[x-1] and test.isnull()[x]):
s = df.ix[:x,'start'].last_valid_index()
df.ix[s:x-1,'end'] = df.ix[x-1, 'Date']
#find valley
v = df.ix[s:x-1,'vami'].idxmin()
df.ix[s:x-1, 'valley'] = df.ix[v,'Date']
df.ix[x-1,'length_of_dd'] = len(df[s:x-1])+1
#need to sum ror's here
df.ix[s:x-1, 'dd'] = pd.expanding_sum(df.ix[s:x-1,'ror'])
df.ix[x-1, 'max_dd'] = np.exp(df.ix[s:v,'ror'].sum())
if (x == len(df)-1 and test.notnull()[x]):
s = df.ix[:x,'start'].last_valid_index()
df.ix[s:x,'end'] = df.ix[x, 'Date']
#find valley
v = df.ix[s:x,'vami'].idxmin()
df.ix[s:x, 'valley'] = df.ix[v,'Date']
df.ix[x,'length_of_dd'] = len(df[s:x])+1
#need to sum ror's here
df.ix[s:x, 'dd'] = pd.expanding_sum(df.ix[s:x,'ror'])
df.ix[x, 'max_dd'] = np.exp(df.ix[s:v,'ror'].sum())
#forward fill the start
df['start'] = df['start'][df['indd'].notnull()].fillna(method='ffill')
return df
def expanding_smoother(self, data, stype='rolling_mean', min_periods=None, freq=None):
"""
Perform a expanding smooting on the data for a complete help refer to http://pandas.pydata.org/pandas-docs/dev/computation.html
:param data: pandas dataframe input data
:param stype: soothing type
:param min_periods: periods
:param freq: frequence
smoothing types:
expanding_count Number of non-null observations
expanding_sum Sum of values
expanding_mean Mean of values
expanding_median Arithmetic median of values
expanding_min Minimum
expanding_max Maximum
expandingg_std Unbiased standard deviation
expanding_var Unbiased variance
expanding_skew Unbiased skewness (3rd moment)
expanding_kurt Unbiased kurtosis (4th moment)
"""
if stype == 'count':
newy = pd.expanding_count(data, min_periods=min_periods, freq=freq)
if stype == 'sum':
newy = pd.expanding_sum(data, min_periods=min_periods, freq=freq)
if stype == 'mean':
newy = pd.expanding_mean(data, min_periods=min_periods, freq=freq)
if stype == 'median':
newy = pd.expanding_median(data, min_periods=min_periods, freq=freq)
if stype == 'min':
newy = pd.expanding_min(data, min_periods=min_periods, freq=freq)
if stype == 'max':
newy = pd.expanding_max(data, min_periods=min_periods, freq=freq)
if stype == 'std':
newy = pd.expanding_std(data, min_periods=min_periods, freq=freq)
if stype == 'var':
newy = pd.expanding_var(data, min_periods=min_periods, freq=freq)
if stype == 'skew':
newy = pd.expanding_skew(data, min_periods=min_periods, freq=freq)
if stype == 'kurt':
newy = pd.expanding_kurt(data, min_periods=min_periods, freq=freq)
return newy
def load_volume_profile(uni_df, start, end, freq='30Min'):
date = start
result_dfs = list()
while (date < end):
dateStr = date.strftime('%Y%m%d')
year = dateStr[0:4]
price_dir = PRICE_BASE_DIR + year
volume_file = price_dir + "/" + dateStr + ".equ_volume_profiles_20d.rev.csv"
print "Loading {}".format(volume_file)
try:
volume_df = pd.read_csv(volume_file, header=0, index_col=['sid'])
except IOError:
print "File not found: {}".format(volume_file)
date += timedelta(days=1)
continue
print "stacking..."
volume_df = volume_df.stack()
volume_df = volume_df.reset_index()
volume_df = volume_df[
(volume_df['level_1'] != 'med_open_volume')
& (volume_df['level_1'] != 'med_close_volume') &
(volume_df['level_1'] != 'med_cum_pre_mkt_volume') &
(volume_df['level_1'] != 'med_cum_post_mkt_volume')]
timemap = dict()
print "parsing dates..."
for rawtime in volume_df['level_1'].unique():
val = None
try:
val = dateparser.parse(dateStr + " " + rawtime[:-2] + ":" +
rawtime[-2:])
except:
pass
timemap[rawtime] = val
print "mapping dates..."
volume_df['iclose_ts'] = volume_df['level_1'].apply(
lambda x: timemap[x])
volume_df['date'] = date
volume_df.set_index(keys=['date', 'sid'], inplace=True)
print "merging..."
volume_df = pd.merge(uni_df,
volume_df,
how='inner',
left_index=True,
right_index=True,
sort=True,
suffixes=['', '_dead'])
volume_df.reset_index(inplace=True)
grouped = volume_df.groupby('sid')
print "accumulating volumes..."
for name, group in grouped:
group['med_cum_volume'] = pd.expanding_sum(group[0])
del group[0]
group['sid'] = name
group = group.reset_index()
# print group.head()
group.set_index('iclose_ts', inplace=True)
group_df = group.resample(freq,
how='last',
closed='right',
label='right')
# print group_df.head()
result_dfs.append(group_df)
date += timedelta(days=1)
result_df = pd.concat(result_dfs)
result_df = result_df.reset_index()
print result_df.head()
result_df['iclose_ts'] = result_df['level_0']
del result_df['level_0']
result_df.set_index(keys=['iclose_ts', 'sid'], inplace=True)
result_df = remove_dup_cols(result_df)
return result_df
df
# <headingcell level=3>
# Generate a Linear Regression of the data
# <codecell>
from datetime import timedelta
tdf = df.groupby(['Patient', 'Visit'], as_index=False).first()
date_based = pd.pivot_table(tdf[tdf['Date'].notnull()], rows = 'Date',
cols = 'Prediction',
values = 'Patient',
aggfunc = 'count')
date_cum = pd.expanding_sum(date_based)['2013-10':]
date_cum['Total'] = date_cum.sum(axis=1)
td = date_cum[['Total']].reset_index()
td['dDate'] = (td['Date'] - pd.to_datetime('2013-7-1')).apply(lambda x: x / timedelta64(1, 'D'))
m, b, r, p, e = linregress(td['dDate'], td['Total'])
num_days = (len(tdf)-b)/m
nd = pd.DataFrame({
'Date':pd.date_range(start = '2013-7-1',
freq = 'M',
periods = np.ceil(num_days/30))
})
nd['dDate'] = (nd['Date'] - pd.to_datetime('2013-7-1')).apply(lambda x: x / timedelta64(1, 'D'))
nd['GuessNum'] = m*nd['dDate'] + b
nd = nd.set_index('Date')
# Difference functions allow us to identify seasonal changes when we see repeated up or downswings. # An example from FiveThirtyEight: # http://i2.wp.com/espnfivethirtyeight.files.wordpress.com/2015/03/casselman-datalab-wsj2.png?quality=90&strip=all&w=575&ssl=1 ''' Pandas Expanding Functions In addition to the set of rolling_* functions, Pandas also provides a similar collection of expanding_* functions, which, instead of using a window of N values, uses all values up until that time. ''' pd.expanding_mean(daily_store_sales) # average date from first till last date specified pd.expanding_sum(daily_store_sales) # sum of average sales per store until that date ''' EXERCISES 1. Plot the distribution of sales by month and compare the effect of promotions. hint: try using hue in sns 2. Are sales more correlated with the prior date, a similar date last year, or a similar date last month? 3. Plot the 15 day rolling mean of customers in the stores. 4. Identify the date with largest drop in sales from the same date in the previous week. 5. Compute the total sales up until Dec. 2014. 6. When were the largest differences between 15-day moving/rolling averages? HINT: Using rolling_mean and diff ''' # Plot the distribution of sales by month and compare the effect of promotions sns.factorplot(
from pyswing.AskHorse import askHorse
args = "-n asx".split()
askHorse(args)
from pyswing.AnalyseStrategies import analyseStrategies
args = "-n ftse -s v1.2 -r 0.4 -t 500".split
analyseStrategies(args)
# Run me to populate (emptying to begin with) the historic trades table using the strategies in active strategies (which must be put in there manually)...
from pyswing.GenerateHistoricTradesForActiveStrategies import generateHistoricTradesForActiveStrategies
args = "-n ftse".split()
generateHistoricTradesForActiveStrategies(args)
# Run me to chart the (distinct) results in active strategy
import pyswing.database
import sqlite3
from pandas.io.sql import read_sql_query
from pandas import expanding_sum
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
query = ("select t.matchDate as Date, t.code as Code, t.type as Type, t.ExitValue as ExitValue from ( select distinct matchDate, Code, type, exitValue from historicTrades order by matchDate asc) t")
cbaEquityData = read_sql_query(query, connection, 'Date')
connection.close()
cbaEquityData['ExitValueAfterCosts'] = cbaEquityData['ExitValue'] - 0.2
exitValueDataFrame = cbaEquityData.ix[:,'ExitValueAfterCosts']
cbaEquityData["Sum"] = expanding_sum(exitValueDataFrame)
cbaEquityData.query("Date > '2005-01-01 00:00:00'").plot(y=['Sum'], title='v1.4')
df=pd.concat(l,axis=0)
df.to_csv("/Users/juju/Dropbox/Sent_to_STR_ZHU/miami_aggby_post_month.csv")
#### In excel, arrange the column names
df = pd.read_csv("/Users/juju/Dropbox/Sent_to_STR_ZHU/chicago_aggby_post_month.csv",sep=',',header=0,infer_datetime_format=True,parse_dates=['review_month'])
df["review_month"] = df["review_month"].dt.to_period("M")
l=[]
g = df.groupby("shareid")
for name,group in g:
group["accum_rating"] = pd.expanding_mean(group["month_rating_mean"])
group["num_of_reviews"] = pd.expanding_sum(group["monthly_reviews"])
group["num_of_responses"] = pd.expanding_sum(group["monthly_hotel_response"])
group["num_of_partnerships"] = pd.expanding_sum(group["partnerships"])
group["num_of_solo"] = pd.expanding_sum(group["solo"])
group["num_of_couple"] = pd.expanding_sum(group["couple"])
group["num_of_family"] = pd.expanding_sum(group["family"])
group["num_of_business"] = pd.expanding_sum(group["business"])
group["shareid"]=name
l.append(group)
df_2= pd.concat(l,axis=0)
df_2.to_csv("/Users/juju/Dropbox/Sent_to_STR_ZHU/chicago_aggby_post_month_2.csv", index = False)
# Aggregate by stayed month
y=['Close', 'SMA_200'], title='Testing')
from pyswing.AskHorse import askHorse
args = "-n asx".split()
askHorse(args)
from pyswing.AnalyseStrategies import analyseStrategies
args = "-n ftse -s v1.2 -r 0.4 -t 500".split
analyseStrategies(args)
# Run me to populate (emptying to begin with) the historic trades table using the strategies in active strategies (which must be put in there manually)...
from pyswing.GenerateHistoricTradesForActiveStrategies import generateHistoricTradesForActiveStrategies
args = "-n ftse".split()
generateHistoricTradesForActiveStrategies(args)
# Run me to chart the (distinct) results in active strategy
import pyswing.database
import sqlite3
from pandas.io.sql import read_sql_query
from pandas import expanding_sum
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
query = (
"select t.matchDate as Date, t.code as Code, t.type as Type, t.ExitValue as ExitValue from ( select distinct matchDate, Code, type, exitValue from historicTrades order by matchDate asc) t"
)
cbaEquityData = read_sql_query(query, connection, 'Date')
connection.close()
cbaEquityData['ExitValueAfterCosts'] = cbaEquityData['ExitValue'] - 0.2
exitValueDataFrame = cbaEquityData.ix[:, 'ExitValueAfterCosts']
cbaEquityData["Sum"] = expanding_sum(exitValueDataFrame)
cbaEquityData.query("Date > '2005-01-01 00:00:00'").plot(y=['Sum'],
title='v1.4')
def analyse(self):
# Logger.log(logging.INFO, "Analyse Strategy", {"scope":__name__, "Rule 1":self._rule1, "Rule 2":self._rule2, "Rule 3":self._rule3, "Type":self._type})
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
query = self.analyseStrategySql % (self._rule1, self._rule2,
self._rule3, self._exit, self._type)
self._strategyData = read_sql_query(query, connection, 'Date')
self._strategyData[
'ExitValueAfterCosts'] = self._strategyData['ExitValue'] - 0.2
connection.close()
exitValueDataFrame = self._strategyData.ix[:, 'ExitValueAfterCosts']
mean = exitValueDataFrame.mean()
median = exitValueDataFrame.median()
sum = exitValueDataFrame.sum()
count = exitValueDataFrame.count()
tradesPerYear = count / 10
sharpeRatio = sqrt(tradesPerYear) * exitValueDataFrame.mean(
) / exitValueDataFrame.std()
self._strategyData["Sum"] = expanding_sum(exitValueDataFrame)
self._strategyData["Max"] = expanding_max(self._strategyData["Sum"])
self._strategyData["Min"] = expanding_min(self._strategyData["Sum"])
self._strategyData[
"DD"] = self._strategyData["Max"] - self._strategyData["Min"]
runningSum = expanding_sum(exitValueDataFrame)
max2here = expanding_max(runningSum)
dd2here = runningSum - max2here
drawDown = dd2here.min()
Logger.log(
logging.INFO, "Analysing Strategy", {
"scope": __name__,
"Rule 1": self._rule1,
"Rule 2": self._rule2,
"Rule 3": self._rule3,
"Exit": self._exit,
"Type": self._type,
"Mean": str(mean),
"Median": str(median),
"Sum": str(sum),
"Count": str(count),
"SharpeRatio": str(sharpeRatio),
"DrawDown": str(drawDown)
})
connection = sqlite3.connect(pyswing.database.pySwingDatabase)
c = connection.cursor()
deleteSql = self.deleteStrategySql % (
pyswing.globals.pySwingStrategy, self._rule1, self._rule2,
self._rule3, self._exit, self._type)
c.executescript(deleteSql)
connection.commit()
insertSql = self.insertStrategySql % (
pyswing.globals.pySwingStrategy, self._rule1, self._rule2,
self._rule3, self._exit, self._type, str(mean), str(median),
str(sum), str(count), str(sharpeRatio), str(drawDown))
c.executescript(insertSql)
connection.commit()
c.close()
connection.close()
def prepare_data(kind):
if kind == 'f': # If fall
putList, takeList = fall_df_list, fall_list
else: # If ADL
putList, takeList = adl_df_list, adl_list
start = time.time() # Timer for testing
for i in range(0, len(
takeList)): # Iterate through the takeList (fall_list or adl_list)
my_df = takeList[i].copy() # copy dataframe from list
new_df = pd.DataFrame() # placeholder
for trial in trials: # Iterate through trials (1-5)
# Get relevant trial data
trial_df = my_df[my_df['trial'] == trial]
tempdf = pd.DataFrame() # dataframe for putting into filter
# Low Pass Buttersworth Filter and remove bias
tempdf['ax'], tempdf['ay'], tempdf['az'] = trial_df[
'x1'], trial_df['y1'], trial_df['z1']
tempdf = tempdf.reset_index(drop=True)
tempdf['fx'] = pd.Series(
butter_lowpass_filter(trial_df['x1'], cutoff, fs, order))
tempdf['fy'] = pd.Series(
butter_lowpass_filter(trial_df['y1'], cutoff, fs, order))
tempdf['fz'] = pd.Series(
butter_lowpass_filter(trial_df['z1'], cutoff, fs, order))
tempdf['bx'] = tempdf['fx'].diff()
tempdf['by'] = tempdf['fy'].diff()
tempdf['bz'] = tempdf['fz'].diff()
tempdf = tempdf.reset_index(drop=True)
trial_df = trial_df.reset_index(drop=True)
tempdf['gx'], tempdf['gy'], tempdf['gz'] = trial_df[
'x2'], trial_df['y2'], trial_df['z2']
# Rolling averages
tempdf['y_roll'] = pd.Series(tempdf['by'].rolling(200).mean())
tempdf['fy_roll'] = pd.Series(tempdf['fy'].rolling(200).mean())
tempdf['gy_roll'] = pd.Series(tempdf['by'].rolling(200).mean())
# Rolling standard deviations
tempdf['bx_std'] = tempdf['bx'].rolling(200).std()
tempdf['by_std'] = tempdf['by'].rolling(200).std()
tempdf['bz_std'] = tempdf['bz'].rolling(200).std()
tempdf['fx_std'] = tempdf['fx'].rolling(200).std()
tempdf['fy_std'] = tempdf['fy'].rolling(200).std()
tempdf['fz_std'] = tempdf['fz'].rolling(200).std()
tempdf['gx_std'] = tempdf['fx'].rolling(200).std()
tempdf['gy_std'] = tempdf['fy'].rolling(200).std()
tempdf['gz_std'] = tempdf['fz'].rolling(200).std()
# Integral stuff
tempdf['xsum'] = pd.expanding_sum(
((abs(tempdf['ax']).rolling(2).sum() / 2) *
(1 / 200)).fillna(0))
tempdf['ysum'] = pd.expanding_sum(
((abs(tempdf['ay']).rolling(2).sum() / 2) *
(1 / 200)).fillna(0))
tempdf['zsum'] = pd.expanding_sum(
((abs(tempdf['az']).rolling(2).sum() / 2) *
(1 / 200)).fillna(0))
tempdf['time'] = 1 / 200
tempdf['time'] = pd.expanding_sum(tempdf['time'])
# C10 Signal Magnitude Area
tempdf['SigMagArea'] = (tempdf['xsum'] + tempdf['ysum'] +
tempdf['zsum']) / tempdf['time']
# C11
tempdf['HorizSigMagArea'] = (tempdf['xsum'] +
tempdf['zsum']) / tempdf['time']
# Sum vector magnitude
tempdf['vm'] = np.sqrt(tempdf['fx']**2 + tempdf['fy']**2 +
tempdf['fz']**2)
# Maximum peak to peak acceleration amplitude
tempdf['Amax'] = (tempdf['vm'].rolling(200).max())
tempdf['Amin'] = (tempdf['vm'].rolling(200).min())
# C3
tempdf['peak_diff'] = tempdf['Amax'] - tempdf['Amin']
# Angle from horizontal to z-axis
tempdf['angle_from_horiz'] = np.arctan2(
np.sqrt(tempdf['fx']**2 + tempdf['fz']**2),
-tempdf['fy']) * 180 / np.pi
tempdf['angle_std'] = pd.rolling_std(tempdf['angle_from_horiz'],
200)
# had to make versions of this to put into sliding window, will change once I
# confirm they're the same as the others below
tempdf['horiz_std_mag9'] = np.sqrt(tempdf['fx_std']**2 +
tempdf['fz_std']**2)
tempdf['horiz_vector_mag9'] = np.sqrt(tempdf['fx']**2 +
tempdf['fz']**2)
tempdf['std_mag9'] = np.sqrt(tempdf['fx_std']**2 +
tempdf['fy_std']**2 +
tempdf['fz_std']**2)
tempdf['diff_std_mag9'] = np.sqrt(tempdf['bx_std']**2 +
tempdf['by_std']**2 +
tempdf['bz_std']**2)
tempdf['horiz_mag2'] = np.sqrt(tempdf['bx']**2 + tempdf['bz']**2)
tempdf['horiz_std_mag2'] = np.sqrt(tempdf['bx_std']**2 +
tempdf['bz_std']**2)
tempdf['vector_mag2'] = np.sqrt(tempdf['bx']**2 + tempdf['by']**2 +
tempdf['bz']**2)
tempdf['gyro_horiz_std_mag'] = np.sqrt(tempdf['gx_std']**2 +
tempdf['gz_std']**2)
tempdf['gyro_vector_mag'] = np.sqrt(tempdf['gx']**2 +
tempdf['gy']**2 +
tempdf['gz']**2)
tempdf['gyro_horiz_mag'] = np.sqrt(tempdf['gx']**2 +
tempdf['gz']**2)
tempdf['gyro_std_mag'] = np.sqrt(tempdf['gx_std']**2 +
tempdf['gy_std']**2 +
tempdf['gz_std']**2)
tempdf = pd.concat([
tempdf.reset_index(drop=True), trial_df[[
'activity', 'subject', 'trial'
]].reset_index(drop=True)
],
axis=1)
new_df = pd.concat([new_df.reset_index(drop=True), tempdf])
sliding_window(tempdf, kind)
# differential vector mag
new_df['vector_mag'] = np.sqrt(new_df['fx']**2 + new_df['fy']**2 +
new_df['fz']**2)
# C2
new_df['horiz_mag'] = np.sqrt(new_df['fx']**2 + new_df['fz']**2)
#
new_df['vert'] = new_df['by'] - new_df['y_roll']
new_df['vert2'] = new_df['ay'] - new_df['y_roll']
new_df['vert3'] = new_df['fy'] - new_df['fy_roll']
# C9
new_df['std_mag2'] = np.sqrt(new_df['bx_std']**2 +
new_df['by_std']**2 + new_df['bz_std']**2)
putList.append(new_df.fillna(0))
print('Completed... It took', time.time() - start, 'seconds.')
def SUM(self, param):
if param[1] == 0:
return pd.expanding_sum(param[0])
return pd.rolling_sum(param[0], param[1])