##Hi everyone this is my first portfolio project on my data analysis way. So lets see some interesting observations :)

###Firstly lets import our datasets and download librarys

  library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
  library(ggplot2)
  library(readxl)
  sleepDay_merged <- read_excel("/Users/illya/portfolio/sleepDay_merged.xlsx")
 
  library(readxl)
  Електронна_таблиця_без_назви <- read_excel("/Users/illya/portfolio/dailyActivity_merged.xlsx")
sleepday <- sleepDay_merged
dailact <- Електронна_таблиця_без_назви

###After that let`s explore some heads of datasets

head(sleepday)
## # A tibble: 6 × 5
##           Id SleepDay        TotalSleepRecords TotalMinutesAsleep TotalTimeInBed
##        <dbl> <chr>                       <dbl>              <dbl>          <dbl>
## 1 1503960366 4/12/2016 12:0…                 1                327            346
## 2 1503960366 4/13/2016 12:0…                 2                384            407
## 3 1503960366 4/15/2016 12:0…                 1                412            442
## 4 1503960366 4/16/2016 12:0…                 2                340            367
## 5 1503960366 4/17/2016 12:0…                 1                700            712
## 6 1503960366 4/19/2016 12:0…                 1                304            320
head(dailact)
## # A tibble: 6 × 15
##           Id ActivityDate TotalSteps TotalDistance    TrackerDistance 
##        <dbl> <chr>             <dbl> <chr>            <chr>           
## 1 1503960366 42708.0           13162 45420.0          45420.0         
## 2 1503960366 4/13/2016         10735 6.96999979019165 6.96999979019165
## 3 1503960366 4/14/2016         10460 6.73999977111816 6.73999977111816
## 4 1503960366 4/15/2016          9762 6.28000020980835 6.28000020980835
## 5 1503960366 4/16/2016         12669 8.15999984741211 8.15999984741211
## 6 1503960366 4/17/2016          9705 6.48000001907349 6.48000001907349
## # ℹ 10 more variables: LoggedActivitiesDistance <chr>,
## #   VeryActiveDistance <chr>, ModeratelyActiveDistance <chr>,
## #   LightActiveDistance <chr>, SedentaryActiveDistance <chr>,
## #   VeryActiveMinutes <dbl>, FairlyActiveMinutes <dbl>,
## #   LightlyActiveMinutes <dbl>, SedentaryMinutes <dbl>, Calories <dbl>

###Also we need to check distinct values of two our datasets

n_distinct(sleepday$Id)
## [1] 24
n_distinct(dailact$Id)
## [1] 33

###Let`s quick summarry some statistics in first stat

dailact %>%
  select(TotalSteps,
         TotalDistance,
         SedentaryMinutes) %>%
  summary()
##    TotalSteps    TotalDistance      SedentaryMinutes
##  Min.   :    0   Length:940         Min.   :   0.0  
##  1st Qu.: 3790   Class :character   1st Qu.: 729.8  
##  Median : 7406   Mode  :character   Median :1057.5  
##  Mean   : 7638                      Mean   : 991.2  
##  3rd Qu.:10727                      3rd Qu.:1229.5  
##  Max.   :36019                      Max.   :1440.0

###And in second stat

sleepday %>% 
  na.omit()%>% 
  select(TotalMinutesAsleep,TotalSleepRecords,TotalTimeInBed) %>% 
  summary()
##  TotalMinutesAsleep TotalSleepRecords TotalTimeInBed 
##  Min.   : 58.0      Min.   :1.000     Min.   : 61.0  
##  1st Qu.:361.0      1st Qu.:1.000     1st Qu.:403.0  
##  Median :433.0      Median :1.000     Median :463.0  
##  Mean   :419.5      Mean   :1.119     Mean   :458.6  
##  3rd Qu.:490.0      3rd Qu.:1.000     3rd Qu.:526.0  
##  Max.   :796.0      Max.   :3.000     Max.   :961.0

###After all of this analyze work, let`s vizualise our data

ggplot(data = sleepday, aes(x = TotalMinutesAsleep, y = TotalTimeInBed))+ geom_point()

###.

ggplot(data=dailact, aes(x=TotalSteps, y=SedentaryMinutes)) + geom_point()

###And in the finish lets combine our datasets

combined_data <- merge(x = sleepday, y = dailact, by="Id")

###Thank you for your time. Enjoy