anirudhjayaraman

---
title: "ARIMA Modeling in R"
output: html_document
---

Let's start off by loading relevant R libraries!
```{r include = FALSE}
library(tseries)
library(zoo)
library(forecast)

anirudhjayaraman

# Code for the merge subroutine

def merge(a,b):
    """ Function to merge two arrays """
    c = []
    while len(a) != 0 and len(b) != 0:
        if a[0] < b[0]:
            c.append(a[0])
            a.remove(a[0])
        else:

anirudhjayaraman

library(xlsx)
library(forecast)
library(tseries)
library(strucchange)

## load the data from a CSV or Excel file. This example is done with an Excel sheet.
prod_df <- read.xlsx(file = 'agricultural_productivity.xls', sheetIndex = 'Sheet1', rowIndex = 8:65, colIndex = 2, header = FALSE)
colnames(prod_df) <- c('Rice')
## store rice data as time series objects
rice <- ts(prod_df$Rice, start=c(1951, 1), end=c(2008, 1), frequency=1) 

anirudhjayaraman

remove_missing_levels <- function(fit, test_data) {
  library(magrittr)
  
  # https://stackoverflow.com/a/39495480/4185785
  
  # drop empty factor levels in test data
  test_data %>%
    droplevels() %>%
    as.data.frame() -> test_data
  

anirudhjayaraman

rm(list = ls())

# Load relevant libraries -----------------------------------------------------
library(stringr)
library(data.table)

# =============================================================================
# COVID 19-India API: A volunteer-driven, crowdsourced database 
# for COVID-19 stats & patient tracing in India
# =============================================================================

anirudhjayaraman

anirudhjayaraman

# prints recursive count of lines of python source code from current directory
# includes an ignore_list. also prints total sloc

import os
cur_path = os.getcwd()
ignore_set = set(["__init__.py", "count_sourcelines.py"])

loclist = []

for pydir, _, pyfiles in os.walk(cur_path):

anirudhjayaraman

anirudhjayaraman

library(data.table)

train <- fread('train.csv'); test <- fread('test.csv')

# consolidate the 2 data sets after creating a variable indicating train / test 
train$flag <- 0; test$flag <- 1
dat <- rbind(train,test)

# change outcome, var_b and var_e into factor var
dat$outcome <- factor(dat$outcome)

anirudhjayaraman

# assuming you have a 'ts' object in R 

# 1. install package 'strucchange'
# 2. Then write down this code:

library(strucchange)

# store the breakdates
bp_ts <- breakpoints(ts ~ 1)