04pallav

df.to_excel('test.xlsx', sheet_name='sheet1', index=False)

04pallav

fullDf['forecast_date'].fillna(fullDf.day, inplace=True)

04pallav

calls_final.calls_tw=calls_final.calls_tw.map(lambda x: x if np.isfinite(x) else 0)

04pallav

visits_wd['label_time']=visits_wd['last_date'].map(lambda x: x-relativedelta(months=goback))

df_test1['add']=pd.to_timedelta(df_test1['add'], unit='D')# convert integers to days this way
df_test1['forecast_date']=df_test1['forweek']+df_test1['add']

04pallav

df['date'].dt.weekday_name

04pallav

df.sort_index(inplace=True)    ####will so the df by index in place

04pallav

from datetime import date

def sun_date(input):
    d = input.toordinal()
    last = d 
    sunday = last - (last % 7)
    return date.fromordinal(sunday)
    
# converting to ordunal help calculations

04pallav

Today = datetime.now() 
Today
##############datetime.datetime(2017, 7, 17, 17, 54, 32, 101687)
import pytz

print("#######################################################################################")
print("Step2: rates_calculations.ipynb run started at "+ str(datetime.now(pytz.timezone('America/Los_Angeles')).strftime('%d-%m-%Y %H:%M:%S')))
print("#######################################################################################")

Today = Today.strftime("%Y-%m-%d")

04pallav

from scipy.stats.kde import gaussian_kde
from numpy import linspace
# input data
data = train.loss
# data =randn(10000)
# this create the kernel, given an array it will estimate the probability over that values
kde = gaussian_kde( data )
# these are the values over wich your kernel will be evaluated
dist_space = linspace( min(data), max(data), 100 )
# plot the results

04pallav

train.info()       #### will give a summary for the entire data
train.describe()   #### will give a summary for continuous variables in the data