EPIAS 20201112

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(readxl)
library(dplyr)
library(ggplot2)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(tidyr)

elec_df <- read_xls("/Users/emredemirhan/Desktop/r_exercises/ptf-smf-3.xls")

# tarih ve saatin POSIX formatina cevrilmesi
elec_df <- elec_df %>% mutate(New_Date = 
                              as.POSIXct(elec_df$Date,format="%d.%m.%y %H:%M", "GMT")) %>%
                     select(New_Date, MCP, SMP) %>%
                     rename(Date = New_Date)

# geri kalan 4 sutunun numeric classina cevrilmesi
elec_df[,c(2:3)] <- lapply(elec_df[,c(2:3)],
                          function(x) as.numeric(gsub(",", ".", gsub("\\.", "", x))))

elec_df %>% glimpse()

## Rows: 720
## Columns: 3
## $ Date <dttm> 2020-09-01 00:00:00, 2020-09-01 01:00:00, 2020-09-01 02:00:00, …
## $ MCP  <dbl> 30239, 30025, 29264, 29000, 29000, 29000, 29201, 29539, 30736, 3…
## $ SMP  <dbl> 33239, 32525, 31764, 32000, 33000, 33900, 34201, 34500, 33888, 3…

head(elec_df)

## # A tibble: 6 x 3
##   Date                  MCP   SMP
##   <dttm>              <dbl> <dbl>
## 1 2020-09-01 00:00:00 30239 33239
## 2 2020-09-01 01:00:00 30025 32525
## 3 2020-09-01 02:00:00 29264 31764
## 4 2020-09-01 03:00:00 29000 32000
## 5 2020-09-01 04:00:00 29000 33000
## 6 2020-09-01 05:00:00 29000 33900

plot_1_df<-elec_df %>%
  filter(MCP>SMP) %>%
  group_by(Date) %>%
  arrange(Date)

ggplot(plot_1_df, aes(x=MCP, y=SMP, color=Date)) +
  geom_point()

plot_2_df<-elec_df %>%
  mutate(Gün = as_date(Date))

plot_2_df

## # A tibble: 720 x 4
##    Date                  MCP   SMP Gün       
##    <dttm>              <dbl> <dbl> <date>    
##  1 2020-09-01 00:00:00 30239 33239 2020-09-01
##  2 2020-09-01 01:00:00 30025 32525 2020-09-01
##  3 2020-09-01 02:00:00 29264 31764 2020-09-01
##  4 2020-09-01 03:00:00 29000 32000 2020-09-01
##  5 2020-09-01 04:00:00 29000 33000 2020-09-01
##  6 2020-09-01 05:00:00 29000 33900 2020-09-01
##  7 2020-09-01 06:00:00 29201 34201 2020-09-01
##  8 2020-09-01 07:00:00 29539 34500 2020-09-01
##  9 2020-09-01 08:00:00 30736 33888 2020-09-01
## 10 2020-09-01 09:00:00 31482 34582 2020-09-01
## # … with 710 more rows

ggplot(plot_2_df, aes(x=MCP, y=SMP, color=Gün)) +
            geom_point() 

plot_3_df <- elec_df %>% 
            mutate(Date = as_date(Date)) %>% 
            group_by(Date) %>% 
            summarise(MCP= mean(MCP), SMP= mean(SMP)) %>% 
            ungroup() %>%
            pivot_longer(cols=c(MCP, SMP), names_to="Market_Imbalance", values_to="Prices")

## `summarise()` ungrouping output (override with `.groups` argument)

ggplot(plot_3_df, aes(x=Date, y=Prices, color=Market_Imbalance)) +
           geom_line()

plot_3_df<- elec_df %>%
  mutate(Date= as_date(Date)) %>%
  group_by(Date) %>%
  summarise(MCP= mean(MCP), SMP=mean(SMP)) %>%
  ungroup() %>%
  pivot_longer(cols=c(MCP, SMP), names_to="Market_Imbalance", values_to="Prices")

## `summarise()` ungrouping output (override with `.groups` argument)

plot_3_df

## # A tibble: 60 x 3
##    Date       Market_Imbalance Prices
##    <date>     <chr>             <dbl>
##  1 2020-09-01 MCP              32203.
##  2 2020-09-01 SMP              37036.
##  3 2020-09-02 MCP              33804.
##  4 2020-09-02 SMP              38894.
##  5 2020-09-03 MCP              33749.
##  6 2020-09-03 SMP              38371.
##  7 2020-09-04 MCP              30880.
##  8 2020-09-04 SMP              34445.
##  9 2020-09-05 MCP              29006.
## 10 2020-09-05 SMP              22948.
## # … with 50 more rows