cyclistic.rmd

---
title: Cyclists Case Study
author: 'Sakshi Gupta'
output: pdf_document
date: "`r Sys.Date()`"
---

## Setting up my enviroment 

```{r message=FALSE, warning=FALSE}
library(dplyr)
library(tidyr)
library(ggplot2)
library(RColorBrewer)
library(scales)
```

## loading required datasets
```{r warning=FALSE}
setwd("C:/Users/HP/Documents/Sakshi/")

df_1<-read.csv("202301-divvy-tripdata.csv")
df_2<-read.csv("202302-divvy-tripdata.csv")
df_3<-read.csv("202303-divvy-tripdata.csv")
df_4<-read.csv("202304-divvy-tripdata.csv")
df_5<-read.csv("202305-divvy-tripdata.csv")
df_6<-read.csv("202306-divvy-tripdata.csv")
df_7<-read.csv("202307-divvy-tripdata.csv")
df_8<-read.csv("202308-divvy-tripdata.csv")
df_9<-read.csv("202309-divvy-tripdata.csv")
df_10<-read.csv("202310-divvy-tripdata.csv")
df_11<-read.csv("202311-divvy-tripdata.csv")
df_12<-read.csv("202312-divvy-tripdata.csv")

```


## combining data in one data frame

```{r warning=FALSE}
df<-bind_rows(df_1,df_2,df_3,df_4, df_5, df_6 , df_7 , df_8 , df_9 , df_10, df_11, df_12)

```

## Exploring the Data
```{r warning=FALSE}

head(df)
str(df)
summary(df)

```

## Standardizing date
```{r warning=FALSE}
df$started_at<-strptime(df$started_at,format="%Y-%m-%d %H:%M:%S")
df$ended_at<-strptime(df$ended_at,format="%Y-%m-%d %H:%M:%S")
```

## Converting column type to factor
```{r warning=FALSE}
unique(df$rideable_type)
df<-df %>% mutate(rideable_type=factor(rideable_type))
unique(df$member_casual)
df<- df%>% mutate(member_casual=factor(member_casual))
```


## checking for Na values
```{r warning=FALSE}
summarise(df,across(everything(),~sum(is.na(.))))
```

## checking distinct values in each column
```{r warning=FALSE}
summarise(df, across(everything(),~sum(n_distinct(.))))
```


## adding appropriate columns
```{r warning=FALSE}
df <-df %>% mutate(ride_length=ended_at-started_at, .after = ended_at) %>% mutate(ride_length=ride_length/60)
df<- df %>% mutate(wkday=weekdays(started_at)) %>% mutate(wkday=factor(wkday,levels=c('Monday','Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday')))
df$ride_length<-as.numeric(df$ride_length)
df <- df %>% mutate(mnth=months(started_at)) %>% mutate(mnth = factor(mnth, levels = c('January','February',"March"   ,  "April"  ,   "May"    ,   "June"    ,  "July"     , "August" , "September", "October"  , "November" , "December" )))
```

## Filtering out negative ride length
```{r warning=FALSE}
df<-filter(df,ride_length>=0)
```

## No, of Different Users
```{r warning=FALSE}
df%>% count(member_casual) %>% ggplot(aes(x=member_casual , y=n, fill=member_casual))+geom_col() +
  theme( axis.text.x = element_blank() ,  
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5, ) +
  labs(  x='Member Type' ,y= "No. of Members " , title= "Casual Riders and Members", fill='Member Type') + 
  scale_fill_brewer(palette = "Set3") +
  scale_y_continuous(labels = label_number())
```

## trip duration Boxplot
```{r warning=FALSE}
df %>% 
  ggplot(aes(y=ride_length, x=member_casual, fill=member_casual))+geom_boxplot()+ ylim(0,100) +
  theme( axis.text.x = element_blank() ,  
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5) +
  labs(fill=" Usertype ", x="Usertype" , y= "Trip Duration (in minutes)" , title= "Trip Duration ") + 
  scale_fill_brewer(palette = "Set3") 
```

## Ridetype
```{r warning=FALSE}
df%>% count(rideable_type) %>% ggplot(aes(x=rideable_type , y=n, fill=rideable_type))+geom_col() +
  theme( axis.text.x = element_blank() ,  
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5, ) +
  labs(x="Ride Type", y= "No. of Members " , title= "Preferred Ride type", fill='Ride Type') + 
  scale_fill_brewer(palette = "Set3") +
  scale_y_continuous(labels = label_number() ,breaks = pretty_breaks(10))


df%>% group_by(member_casual) %>% count(rideable_type) %>% ggplot(aes(x=rideable_type , y=n, fill=member_casual))+geom_bar(stat='identity', position = 'dodge') +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1),  
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5, ) +
  labs(x="Ride Type", y= "No. of Members " , title= "Preferred Ride type", fill='Ride Type') + 
  scale_fill_brewer(palette = "Set3") +
  scale_y_continuous(labels = label_number(),breaks = pretty_breaks(10))
```

## Ridership during the weekday
```{r warning=FALSE}
df %>% count(wkday) %>% ggplot(aes(x=wkday , y=n, fill=wkday))+geom_col() +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1) , 
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5, legend.position = 'none') +
  labs(fill=" Day ", x="Day of the Week" , y= "No. of riders" , title= "Ride Distribution by Weekday") + 
  scale_fill_brewer(palette = "YlGnBu") +
  scale_y_continuous(labels = label_number(),breaks = pretty_breaks(10))

df %>% group_by(member_casual)  %>% count(wkday) %>% ggplot(aes(x=wkday , y=n, fill=member_casual))+geom_bar(stat='identity', position = 'dodge') +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1) , 
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5) +
  labs(fill=" Member Type ", x="Day of the Week" , y= "No. of riders" , title= "Member Distribution during the Week") + 
  scale_fill_brewer(palette = "Set3") +
  scale_y_continuous(labels = label_number(), breaks = pretty_breaks(10))
```

 

## No. of rides by month
```{r warning=FALSE}
df %>% count(mnth) %>%  ggplot(aes(x=mnth , y=n, fill=mnth))+geom_col() +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1) ,  
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5, legend.position = 'none') +
  labs( x="Month" , y= "Frequency " , title= "No. of Rides by Month", fill='Month') + 
  scale_fill_brewer(palette = 'Set3') +
  scale_y_continuous(labels = label_number(),breaks = pretty_breaks(10))

df %>% group_by(member_casual) %>%  count(mnth) %>%  ggplot(aes(x=mnth , y=n, fill=member_casual))+geom_bar(position = 'dodge', stat='identity') +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1) , 
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5) +
  labs( x="Month" , y= "Frequency " , title= "Monthly Bike ride no. by Usertype", fill='User Type') + 
  scale_y_continuous(labels = label_number(), breaks = pretty_breaks(10))+
  scale_fill_brewer(palette = "Set3")
```

## Station with most no. rides
#  Identifying Area names and Top 20 most used stations
```{r warning=FALSE}
df<-df%>% separate(start_station_name, 'from_area', sep=' &', remove=FALSE)
df<-df%>% separate(end_station_name, 'to_area', sep=' &', remove=FALSE)

member_station<-full_join(df %>% filter(member_casual=='member') %>%count(from_area) %>% rename(station_name=from_area),
          df %>%filter(member_casual=='member') %>%  count(to_area) %>% rename(station_name=to_area), 
          by='station_name') %>% 
  filter(station_name!="") %>%
  mutate(freq=n.x+n.y) %>% 
  select(c(station_name, freq))

casual_station<-full_join(df %>% filter(member_casual=='casual') %>%count(from_area) %>% rename(station_name=from_area),
                         df %>%filter(member_casual=='casual') %>%  count(to_area) %>% rename(station_name=to_area), 
                         by='station_name') %>% 
  filter(station_name!="") %>%
  mutate(freq=n.x+n.y) %>% 
  select(c(station_name, freq))

full_join(member_station, casual_station, by="station_name") %>%
  rename(member=freq.x, casual=freq.y) %>%
  mutate(total_freq=(member+casual)) %>%
  arrange(desc(total_freq))%>%
  slice(1:20)%>%
  select(1:3)%>%
  pivot_longer(cols = c('member','casual')) %>%
  group_by(name)%>%
  ggplot(aes(x=station_name, y=value, fill=name))+ 
  geom_bar(position = 'dodge', stat='identity')  +
  theme( axis.text.x = element_text(angle=45, vjust=1, hjust=1) , 
         plot.title = element_text(hjust = 0.5, ),legend.title.align = 0.5) +
  labs( x="Station Name" , y= "Frequency " , title= "Top 20 Most Used Stations", fill='User Type') + 
  scale_y_continuous(labels = label_number(), breaks = pretty_breaks(10))+
  scale_fill_brewer(palette = "Set3")
```