String, datetime, file directory handling in R, Python, PySpark

x <- "1234567890"
nchar(x)

x = "1234567890"
len(x)

print (substr(x, 3, 3))

print (substring(x, 5, 7))

print x[2:3]
print x[4:7]

sub('123', '567', x)      # Changes only the 1st pattern match per string

x = gsub('567', 123, x)   # Changes every occurrence of a pattern match
print (x)

print x.replace('123', '567')  # Changes every occurrence of a pattern match
x = x.replace('567', '123')
print x

substr(x, 4, 4) <- "A"
print (x)

substring(x, 9, 12) <- "ABCD"
print (x)

print (unlist(regexpr('123', x)[1]))    # Returns position of 1st match in a string

print (unlist(gregexpr('123', x)))      # Returns positions of every match in a string

print x
print x.find('123')         # Returns position of 1st match in a string
print x.find('89', 0, 7)

import re
print [(a.start(), a.end()) for a in list(re.finditer('123', x))]    # Returns positions of every match in a string

print (paste("123", "456", sep=""))

print (paste("123", "456", sep=","))

print "123" + "456"
print "123" + "," + "456"

unlist(strsplit(x, "A"))

x = "123A1238AB"
print x.split("A")     # split all occurrences
print x.split("A", 1)  # limit to specific number of splits 

y = 'aBCDE'
toupper(substring(y, 1, 1))

tolower(substring(y, 2, nchar(y)))

y = 'abCDE'
print y.upper()
print y.lower()

name <- c('Apple', 'Bill', 'Chris', 'Daniel', 'Eric')
birthyear <- c(2012, 2012, 2013, 2014, 2014)
df <- data.frame(name, birthyear, stringsAsFactors = FALSE)
print(df)

toupper(df$name)

import pandas as pd
import numpy as np
data = {'name': ['Apple', 'Bill', 'Chris', 'Daniel', 'Eric'], 'birthyear': [2012, 2012, 2013, 2014, 2014]}
df = pd.DataFrame(data)
print (df.dtypes)
print (df)
df['name'] = df['name'].apply(lambda x: x.upper())
df['birthyear'] = df['birthyear'].astype('str')
print (df.dtypes)
print (df)

today <- Sys.Date()
print (format(today, format="%B %d %Y"))

str(today)

current <- Sys.time()                 
print (format(current, "%Y-%m-%d %I:%M:%S%p"))

str(current)

current_str <- date()
print (current_str)

str(current_str)

import time
print "Current date %s" % time.strftime('%b %d, %Y')
print "Current date & time " + time.strftime("%c")

import datetime
i = datetime.datetime.now()
print i
print "Current date = %s/%s/%s" % (i.month, i.day, i.year)

time <- strptime(date(), format="%a %b %d %H:%M:%S %Y")
str(time)

import datetime

dt = datetime.datetime.strptime("2016-09-28 20:30:55.78200", '%Y-%m-%d %H:%M:%S.%f')
print dt
print type(dt)

dt1 <- as.Date('2017-03-15')
dt2 <- as.Date('2017-05-16')

print (difftime(dt2, dt1, units="days"))

print (difftime(dt2, dt1, units="weeks"))

from datetime import datetime
 
dt1 = datetime(2017, 3, 15)
dt2 = datetime(2017, 5, 16)
print dt2 - dt1, ' days'
print (dt2 - dt1).days / 7.0, ' weeks'

print (dt2 + 20)

print (dt2 - 20)

from datetime import datetime, timedelta

before = dt2 + timedelta(days=20)
print before
after = dt2 - timedelta(days=20)
print after 

tm1 <- as.POSIXct("2017-05-24 23:55:26")
tm2 <- as.POSIXct("25052017 08:32:07", format = "%d%m%Y %H:%M:%S")

print (difftime(tm2, tm1, units="hours"))

print (difftime(tm2, tm1, units="mins"))

print (difftime(tm2, tm1, units="secs"))

from datetime import datetime, timedelta
 
tm1 = datetime(2017, 5, 24, 23, 55, 26)
tm2 = datetime(2017, 5, 25, 8, 32, 7 )

diff = tm2 - tm1
secs = diff.total_seconds()
hours = float(secs / 3600)
minutes = float(secs / 60)

print hours, " hours"
print minutes, " minutes"
print secs, " seconds"

print (tm1 + 30)

print (tm1 - 30)

from datetime import datetime, timedelta

tm1 = datetime(2017, 5, 24, 23, 55, 26)
tm2 = datetime(2017, 5, 25, 8, 32, 7 )

before = tm1 + timedelta(seconds=30)
print before
after = tm1 - timedelta(seconds=30)
print after

import numpy as np
import pandas as pd
Aug = ['2018-08-01', '2018-08-02', '2018-08-03', '2018-08-04']
Sept = ['2018-09-01 10:00:000', '2018-09-02 11:00:000', '2018-09-03 12:00:000', '2018-09-04 13:00:000']
df = pd.DataFrame(np.column_stack([Aug, Sept]), columns=['Aug', 'Sept'])
print(df.dtypes)
df['Aug'] = pd.to_datetime(df['Aug'])
df['Sept'] = pd.to_datetime(df['Sept'])
print(df.dtypes)
print(df)