This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(readr)
# Read the CSV file
bike_data <- read_csv("C:/Users/os/Desktop/bikes.csv")
## Rows: 731 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (9): season, holiday, weekday, weather, temperature, realfeel, humidity...
## date (1): date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
head(bike_data)
## # A tibble: 6 × 10
## date season holiday weekday weather temperature realfeel humidity
## <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2011-01-01 1 0 6 2 46.7 46.4 0.806
## 2 2011-01-02 1 0 0 2 48.4 45.2 0.696
## 3 2011-01-03 1 0 1 1 34.2 25.7 0.437
## 4 2011-01-04 1 0 2 1 34.5 28.4 0.590
## 5 2011-01-05 1 0 3 1 36.8 30.4 0.437
## 6 2011-01-06 1 0 4 1 34.9 30.9 0.518
## # ℹ 2 more variables: windspeed <dbl>, rentals <dbl>
1:is there is a relationship between the no of bikee rentals and any of other variables?
Perform multilinearRegression
model <- lm(rentals ~ season + holiday + weekday + weather + temperature + realfeel + humidity + windspeed, data = bike_data)
# Print summary of the regression model
summary(model)
##
## Call:
## lm(formula = rentals ~ season + holiday + weekday + weather +
## temperature + realfeel + humidity + windspeed, data = bike_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4355.7 -969.0 -219.4 1056.3 3916.6
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2512.37 451.00 5.571 3.58e-08 ***
## season 405.26 48.79 8.307 4.85e-16 ***
## holiday -574.56 298.92 -1.922 0.0550 .
## weekday 60.54 25.03 2.419 0.0158 *
## weather -481.99 119.94 -4.019 6.47e-05 ***
## temperature 28.40 25.49 1.114 0.2656
## realfeel 30.94 20.55 1.505 0.1326
## humidity -2301.19 476.26 -4.832 1.65e-06 ***
## windspeed -75.62 16.82 -4.497 8.04e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1340 on 722 degrees of freedom
## Multiple R-squared: 0.5264, Adjusted R-squared: 0.5212
## F-statistic: 100.3 on 8 and 722 DF, p-value: < 2.2e-16
Q2:is there a relationship how strong it ?
correlations <- cor(bike_data[c("rentals", "season", "holiday", "weekday", "weather", "temperature", "realfeel", "humidity", "windspeed")])
print(correlations)
## rentals season holiday weekday weather
## rentals 1.00000000 0.406100371 -0.068347716 0.0674434124 -0.29739124
## season 0.40610037 1.000000000 -0.010536659 -0.0030798813 0.01921103
## holiday -0.06834772 -0.010536659 1.000000000 -0.1019602689 -0.03462684
## weekday 0.06744341 -0.003079881 -0.101960269 1.0000000000 0.03108747
## weather -0.29739124 0.019211028 -0.034626841 0.0310874694 1.00000000
## temperature 0.62749401 0.334314856 -0.028555535 -0.0001699624 -0.12060224
## realfeel 0.63106570 0.342875613 -0.032506692 -0.0075371318 -0.12158335
## humidity -0.10065856 0.205444765 -0.015937479 -0.0522321004 0.59104460
## windspeed -0.23454500 -0.229046337 0.006291507 0.0142821241 0.03951106
## temperature realfeel humidity windspeed
## rentals 0.6274940090 0.631065700 -0.10065856 -0.234544997
## season 0.3343148564 0.342875613 0.20544476 -0.229046337
## holiday -0.0285555350 -0.032506692 -0.01593748 0.006291507
## weekday -0.0001699624 -0.007537132 -0.05223210 0.014282124
## weather -0.1206022365 -0.121583354 0.59104460 0.039511059
## temperature 1.0000000000 0.991701553 0.12696294 -0.157944120
## realfeel 0.9917015532 1.000000000 0.13998806 -0.183642967
## humidity 0.1269629390 0.139988060 1.00000000 -0.248489099
## windspeed -0.1579441204 -0.183642967 -0.24848910 1.000000000
1 indicates a perfect positive linear relationship, -1 indicates a perfect negative linear relationship, and 0 indicates no linear relationship.
Q3:IS THE RELATION IS LINEAR?
# Scatter plot between rentals and season
plot(bike_data$season, bike_data$rentals, xlab = "Season", ylab = "Rentals", main = "Rentals vs. Season")
# Scatter plot between rentals and holiday
plot(bike_data$holiday, bike_data$rentals, xlab = "Holiday", ylab = "Rentals", main = "Rentals vs. Holiday")
# Scatter plot between rentals and weekday
plot(bike_data$weekday, bike_data$rentals, xlab = "Weekday", ylab = "Rentals", main = "Rentals vs. Weekday")
# Scatter plot between rentals and weather
plot(bike_data$weather, bike_data$rentals, xlab = "Weather", ylab = "Rentals", main = "Rentals vs. Weather")
# Scatter plot between rentals and temperature
plot(bike_data$temperature, bike_data$rentals, xlab = "Temperature", ylab = "Rentals", main = "Rentals vs. Temperature")
# Scatter plot between rentals and realfeel
plot(bike_data$realfeel, bike_data$rentals, xlab = "Real Feel", ylab = "Rentals", main = "Rentals vs. Real Feel")
# Scatter plot between rentals and humidity
plot(bike_data$humidity, bike_data$rentals, xlab = "Humidity", ylab = "Rentals", main = "Rentals vs. Humidity")
# Scatter plot between rentals and windspeed
plot(bike_data$windspeed, bike_data$rentals, xlab = "Windspeed", ylab = "Rentals", main = "Rentals vs. Windspeed")
Q4:if relationship is linear how will you quantify the effect of
variable on the no of bike rentals?
# Perform multilinear regression
model <- lm(rentals ~ season + holiday + weekday + weather + temperature + realfeel + humidity + windspeed, data = bike_data)
# Print summary of the regression model
summary(model)
##
## Call:
## lm(formula = rentals ~ season + holiday + weekday + weather +
## temperature + realfeel + humidity + windspeed, data = bike_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4355.7 -969.0 -219.4 1056.3 3916.6
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2512.37 451.00 5.571 3.58e-08 ***
## season 405.26 48.79 8.307 4.85e-16 ***
## holiday -574.56 298.92 -1.922 0.0550 .
## weekday 60.54 25.03 2.419 0.0158 *
## weather -481.99 119.94 -4.019 6.47e-05 ***
## temperature 28.40 25.49 1.114 0.2656
## realfeel 30.94 20.55 1.505 0.1326
## humidity -2301.19 476.26 -4.832 1.65e-06 ***
## windspeed -75.62 16.82 -4.497 8.04e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1340 on 722 degrees of freedom
## Multiple R-squared: 0.5264, Adjusted R-squared: 0.5212
## F-statistic: 100.3 on 8 and 722 DF, p-value: < 2.2e-16
Q5:How accurately we can prdict the no of bike rentals, even future values of each of the relevant variables?
# Split the data into training and testing sets
set.seed(123) # For reproducibility
train_indices <- sample(1:nrow(bike_data), 0.8 * nrow(bike_data)) # 80% for training
train_data <- bike_data[train_indices, ]
test_data <- bike_data[-train_indices, ]
# Train the model on the training data
model <- lm(rentals ~ season + holiday + weekday + weather + temperature + realfeel + humidity + windspeed, data = train_data)
# Make predictions on the testing data
predictions <- predict(model, newdata = test_data)
# Evaluate accuracy
mse <- mean((test_data$rentals - predictions)^2)
mae <- mean(abs(test_data$rentals - predictions))
rsquared <- cor(test_data$rentals, predictions)^2
print(paste("Mean Squared Error (MSE):", mse))
## [1] "Mean Squared Error (MSE): 1853726.7141573"
print(paste("Mean Absolute Error (MAE):", mae))
## [1] "Mean Absolute Error (MAE): 1145.29374211083"
print(paste("R-squared:", rsquared))
## [1] "R-squared: 0.549971159165213"