anirudhjayaraman

# Generate summarizing statistics for hflights
summarise(hflights, n_obs = n(), n_carrier = n_distinct(UniqueCarrier), 
          n_dest = n_distinct(Dest), dest100 = nth(Dest, 100))

# Filter hflights to keep all American Airline flights: aa
aa <- filter(hflights, UniqueCarrier == "American")

# Generate summarizing statistics for aa 
summarise(aa, n_flights = n(), n_canc = sum(Cancelled), 
          p_canc = 100*(n_canc/n_flights), avg_delay = mean(ArrDelay, na.rm = TRUE))

anirudhjayaraman

select(arrange(filter(hflights, DepDelay > 360), TaxiIn + TaxiOut), TailNum)

anirudhjayaraman

# %>% OPERATOR ----------------------------------------------------------------------

# with %>% operator
hflights %>% 
  mutate(diff = TaxiOut - TaxiIn) %>% 
  filter(!is.na(diff)) %>% 
  summarise(avg = mean(diff))

# without %>% operator
# arguments get further and further apart

anirudhjayaraman

# group_by() -------------------------------------------------------------------------

# Generate a per-carrier summary of hflights with the following variables: n_flights, 
# the number of flights flown by the carrier; n_canc, the number of cancelled flights; 
# p_canc, the percentage of cancelled flights; avg_delay, the average arrival delay of 
# flights whose delay does not equal NA. Next, order the carriers in the summary from 
# low to high by their average arrival delay. Use percentage of flights cancelled to 
# break any ties. Which airline scores best based on these statistics?

hflights %>% 

anirudhjayaraman

# Combine group_by with mutate-----

# First, discard flights whose arrival delay equals NA. Next, create a by-carrier 
# summary with a single variable: p_delay, the proportion of flights which are 
# delayed at arrival. Next, create a new variable rank in the summary which is a 
# rank according to p_delay. Finally, arrange the observations by this new rank
hflights %>% 
  filter(!is.na(ArrDelay)) %>% 
  group_by(UniqueCarrier) %>% 
  summarise(p_delay = sum(ArrDelay >0)/n()) %>% 

anirudhjayaraman

## if fxregime or strucchange package is absent from installed packages, download it and load it
if(!require('fxregime')){
  install.packages("fxregime")
}
if(!require('strucchange')){
  install.packages("strucchange")
}

## load packages 
library("fxregime")

anirudhjayaraman

## if fxregime is absent from installed packages, download it and load it
if(!require('fxregime')){
  install.packages("fxregime")
}
## load package 
library("fxregime")
# load the necessary data related to exchange rates - 'FXRatesCHF'
# this dataset treats CHF as unit currency

# install / load Quandl

anirudhjayaraman

def quicksort(x):
    if len(x) == 1 or len(x) == 0:
        return x
    else:
        pivot = x[0]
        i = 0
        for j in range(len(x)-1):
            if x[j+1] < pivot:
                x[j+1],x[i+1] = x[i+1], x[j+1]
                i += 1

anirudhjayaraman

2148
9058
7742
3153
6324
609
7628
5469
7017
504

anirudhjayaraman

#!/usr/bin/env

# Case I
# First element of the unsorted array is chosen as pivot element for sorting using Quick Sort


def countComparisonsWithFirst(x):
    """ Counts number of comparisons while using Quick Sort with first element of unsorted array as pivot """
    global count_pivot_first
    if len(x) == 1 or len(x) == 0: