new docs

Author: sauravhathi

Subjects/INT232 - DATA SCIENCE TOOLBOX R PROGRAMMING/.Rhistory

@@ -0,0 +1,53 @@
+---
+title: "Dashhboard"
+output: 
+  flexdashboard::flex_dashboard:
+    orientation: columns
+    vertical_layout: scroll
+---
+
+```{r setup, include=FALSE}
+library(flexdashboard)
+library(knitr)
+library(ggplot2)
+library(plotly)
+library(dplyr)
+library(openintro)
+
+library(DT)
+library(highcharter)
+```
+
+Column {data-width=650}
+-----------------------------------------------------------------------
+
+### Chart A
+
+```{r}
+ggplot(mpg) +
+  geom_bar(aes(x = class))
+
+```
+
+Column {data-width=500}
+-----------------------------------------------------------------------
+
+### Chart B
+
+```{r}
+ggplot(mtcars, aes(x = drat, y = mpg)) +
+  geom_point()
+
+```
+
+### Chart C
+
+```{r}
+val <-data.frame(course=c('DSA','C++','R','Python'),
+                 num=c(77,55,80,60))
+ggplot(data=val, aes(x=course, y=num, group=1)) +
+  geom_line()+
+  geom_point()
+
+```
+

Subjects/INT232 - DATA SCIENCE TOOLBOX R PROGRAMMING/Dashhboard.Rmd

@@ -0,0 +1,100 @@
+# Define the cars vector with 5 values
+cars <- c(1, 3, 6, 4, 9)
+
+# Graph the cars vector with all defaults
+plot(cars)
+
+# Define the cars vector with 5 values
+cars <- c(1, 3, 6, 4, 9)
+
+# Graph cars using blue points overlayed by a line 
+plot(cars, type="o", col="blue")
+
+# Create a title with a red, bold/italic font
+title(main="Autos", col.main="red", font.main=4)
+
+# Define 2 vectors
+cars <- c(1, 3, 6, 4, 9)
+trucks <- c(2, 5, 4, 5, 12)
+
+# Graph cars using a y axis that ranges from 0 to 12
+plot(cars, type="o", col="blue", ylim=c(0,12))
+
+# Graph trucks with red dashed line and square points
+lines(trucks, type="o", pch=22, lty=2, col="red")
+
+# Create a title with a red, bold/italic font
+title(main="Autos", col.main="red", font.main=4)
+
+# Define 2 vectors
+cars <- c(1, 3, 6, 4, 9)
+trucks <- c(2, 5, 4, 5, 12)
+
+# Calculate range from 0 to max value of cars and trucks
+g_range <- range(0, cars, trucks)
+
+# Graph autos using y axis that ranges from 0 to max 
+# value in cars or trucks vector.  Turn off axes and 
+# annotations (axis labels) so we can specify them ourself
+plot(cars, type="o", col="blue", ylim=g_range, 
+     axes=FALSE, ann=FALSE)
+
+# Make x axis using Mon-Fri labels
+axis(1, at=1:5, lab=c("Mon","Tue","Wed","Thu","Fri"))
+
+# Make y axis with horizontal labels that display ticks at 
+# every 4 marks. 4*0:g_range[2] is equivalent to c(0,4,8,12). labels are parallel (=0) or perpendicular(=2) to axis
+axis(2, las=1, at=4*0:g_range[2])
+
+# Create box around plot
+box()
+
+# Graph trucks with red dashed line and square points
+lines(trucks, type="o", pch=22, lty=2, col="red")
+
+# Create a title with a red, bold/italic font
+title(main="Autos", col.main="red", font.main=4)
+
+# Label the x and y axes with dark green text
+title(xlab="Days", col.lab=rgb(0,0.5,0))
+title(ylab="Total", col.lab=rgb(0,0.5,0))
+
+# Create a legend at (1, g_range[2]) that is slightly smaller 
+# (cex) and uses the same line colors and points used by 
+# the actual plots 
+legend(1, g_range[2], c("cars","trucks"), cex=0.8, 
+       col=c("blue","red"), pch=21:22, lty=1:2);
+
+#Let's start with a simple pie chart graphing the cars vector:
+# Define cars vector with 5 values
+cars <- c(1, 3, 6, 4, 9)
+
+# Create a pie chart for cars
+pie(cars)
+#Now let's add a heading, change the colors, and define our own labels:
+  # Define cars vector with 5 values
+  cars <- c(1, 3, 6, 4, 9)
+
+# Create a pie chart with defined heading and
+# custom colors and labels
+pie(cars, main="Cars", col=rainbow(length(cars)),
+    labels=c("Mon","Tue","Wed","Thu","Fri"))
+data2=c(1,2,4,5,3,3,4,6,7,8)
+data2
+hist(data2)
+colors()
+colours()
+lines(density(data2),lwd=2)
+hist(data2,col='gray75',main=NULL,xlab='size class for data2',ylim=c(0,0.3),freq=FALSE)
+
+dens=density(data2)
+dens
+names(dens)
+str(dens)
+plot(dens$x,dens$y)
+plot(density(data2))
+normde=rnorm(n=500,m=24.2,sd=2.2)
+hist(normde)
+normde$break
+
+     

Subjects/INT232 - DATA SCIENCE TOOLBOX R PROGRAMMING/GRAPHS AND PLOTS.R

@@ -0,0 +1,115 @@
+#***********    GGPLOT2  GRAMMAR OF GRAPHICS     ***********#
+#                                                           #
+#    COMPONENTS OF GRAMMAR OF GRAPHICS                      #
+#    1. DATA        :   the dataset                         #
+#    2. AESTHETICS  :   the metric onto which we plot data  #
+#    3. GEOMETRY    :   visual elements to plot the data    #
+#    4. FACET       :   groups by which we divide the data  #
+#***********************************************************#
+
+library(ggplot2)
+
+#***   SCATTERPLOTS    ***#
+ggplot(data=iris, aes(y=Petal.Length, 
+                      x=Sepal.Length))+geom_point()
+ggplot(data=iris, aes(y=Petal.Length, 
+                      x=Sepal.Length,col=Species))+geom_point()
+ggplot(data=iris, aes(y=Petal.Length, x=Sepal.Length,
+                      shape=Species))+geom_point()
+ggplot(data=iris, aes(y=Petal.Length, x=Sepal.Length, col=Species, 
+                      shape=Species))+geom_point()
+
+str(house)
+
+house<-read.csv(file.choose(),header = TRUE)
+library(dplyr)
+house1<- house[,-1]
+house1 <- house %>% select(c(-1))
+View (house)
+#histogram
+ggplot(data = house, aes(x=price))+ geom_histogram()
+#ggplot(data = house, aes(x=price))+ geom_histogram(bin=50)
+ggplot(data=house,aes(x=price))+
+geom_histogram(bins=50,fill="brown")
+ggplot(data=house, aes(x=price))+
+geom_histogram(bins=50,fill="brown",col="black")
+ggplot(data=house, aes(x=price, fill=air_cond))+geom_histogram
+(bins=50)
+ggplot(data=house, aes(x=price, fill= factor(air_cond)
+))+
+  geom_histogram(bins=50,position="fill")
+
+#*****   BARPLOT   *******#
+#to see distribution of continous variable we use histogram
+#to see distribution of categorical variable we use barplot
+ggplot(data=house, aes(x=waterfront))+geom_bar()
+ggplot(data=house, aes(x=waterfront,
+                      fill=air_cond))+geom_bar()
+ggplot(data=house, aes(x=waterfront,
+                      fill=air_cond))+geom_bar(position = "fill")
+ggplot(data=house, aes(x=waterfront,
+                      fill=sewer))+geom_bar(position="fill")
+
+#****   FREQUENCY-POLYGON   ******#
+# an alternative to a histogram used to see a distribution of continous #variable
+ggplot(data=house, aes(x=price))+geom_freqpoly()
+#increase variation
+ggplot(data=house, aes(x=price))+geom_freqpoly(bins=50)
+ggplot(data=house, aes(x=price))+geom_freqpoly(bins=100)
+ggplot(data=house, aes(x=price, 
+                      col=air_cond))+geom_freqpoly(bins=60)
+
+# Modify formatting of axis
+pl +  scale_x_continuous(labels = comma)
+
+pl +                                                           # Remove axis labels & ticks
+  theme(axis.text.x = element_blank(),
+        axis.ticks.x = element_blank(),
+        axis.text.y = element_blank(),
+        axis.ticks.y = element_blank())
+
+ #****    BOXPLOTS    *****#
+# how does continous var change w.r.t. ategorical var
+#outliers are beyond the avg value
+ggplot(data=house, aes(x=factor(rooms), 
+                      y=price))+geom_boxplot()
+ggplot(data=house, aes(x=factor(rooms), 
+                      y=price, fill=factor(rooms)))+geom_boxplot()
+ggplot(data=house, aes(x=factor(rooms), 
+                      y=price, fill=air_cond))+geom_boxplot()
+ggplot(data=house, aes(x=factor(rooms), 
+                      y=price, fill=sewer))+geom_boxplot()
+
+
+#*****    Smooth-Line    ******#
+#how does one continous variable change w.r.t to other continous var
+ggplot(data=house, 
+       aes(y=price, x=living_area))+geom_smooth()
+
+ggplot(data=house, aes(y=price, x=living_area), 
+                      col=air_cond))+geom_smooth(se=F)
+ggplot(data=house, aes(y=price, x=living_area), 
+                      col=heat))+geom_smooth(se=F)
+
+#**** Applying "lm" (linear model) method   ****#
+ggplot(data=house, aes(y=price, x=living_area))+geom_point()+
+  geom_smooth(method="lm",se=F)
+ggplot(data=house, aes(y=price, x=living_area, 
+                      col=air_cond))+geom_point()+
+  geom_smooth(method="lm",se=F)
+ggplot(data=house, aes(y=price, x=living_area, 
+                      col=heat))+geom_point()+
+  geom_smooth(method="lm",se=F)
+
+##facets
+ggplot(data=house, aes(y=price, x=living_area, 
+                      col=air_cond))+geom_point()+
+  geom_smooth(method="lm",se=F)+facet_grid(~air_cond)
+ggplot(data=house, aes(y=price, x=living_area, 
+                      col=fireplaces))+geom_point()+
+  geom_smooth(method="lm",se=F)+facet_grid(~fireplaces)
+ggplot(data=house, aes(y=price, x=age, 
+                      col=fireplaces))+geom_point()+
+  geom_smooth(method="lm",se=F)+facet_grid(~fireplaces)
+
+