Asdos 2

knitr::opts_chunk$set(echo = TRUE)

netflix = read.csv("netflix_titles.csv")
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.3.3

custom_col = c("red", "green", "blue")
pie <- ggplot(netflix, aes(x = "", fill = factor(type))) +
  geom_bar(width = 1) +
  theme(axis.line = element_blank(),
        plot.title = element_text(hjust = 0.5, size = 22)) +
  labs(fill = "class",
       x = NULL,
       y = NULL,
       title = "Pie Chart of Netflix Shows ") +
  coord_polar(theta = "y", start = 0)
  scale_fill_manual(values = custom_col)

## <ggproto object: Class ScaleDiscrete, Scale, gg>
##     aesthetics: fill
##     axis_order: function
##     break_info: function
##     break_positions: function
##     breaks: waiver
##     call: call
##     clone: function
##     dimension: function
##     drop: TRUE
##     expand: waiver
##     get_breaks: function
##     get_breaks_minor: function
##     get_labels: function
##     get_limits: function
##     get_transformation: function
##     guide: legend
##     is_discrete: function
##     is_empty: function
##     labels: waiver
##     limits: NULL
##     make_sec_title: function
##     make_title: function
##     map: function
##     map_df: function
##     n.breaks.cache: NULL
##     na.translate: TRUE
##     na.value: grey50
##     name: waiver
##     palette: function
##     palette.cache: NULL
##     position: left
##     range: environment
##     rescale: function
##     reset: function
##     train: function
##     train_df: function
##     transform: function
##     transform_df: function
##     super:  <ggproto object: Class ScaleDiscrete, Scale, gg>

pie

ggplot(netflix, aes(x = "", fil = factor(type))) +
  geom_bar(width = 1)

library('dplyr')

## Warning: package 'dplyr' was built under R version 4.3.3

## 
## 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('tidyr')

## Warning: package 'tidyr' was built under R version 4.3.3

library('readr')

## Warning: package 'readr' was built under R version 4.3.3

library('stringr')

## Warning: package 'stringr' was built under R version 4.3.3

library('forcats')

## Warning: package 'forcats' was built under R version 4.3.3

library('modelr')

## Warning: package 'modelr' was built under R version 4.3.3

train = read.csv("train (1).csv")

train$Survived <- factor(train$Survived)
head(train)

##   PassengerId Survived Pclass
## 1           1        0      3
## 2           2        1      1
## 3           3        1      3
## 4           4        1      1
## 5           5        0      3
## 6           6        0      3
##                                                  Name    Sex Age SibSp Parch
## 1                             Braund, Mr. Owen Harris   male  22     1     0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38     1     0
## 3                              Heikkinen, Miss. Laina female  26     0     0
## 4        Futrelle, Mrs. Jacques Heath (Lily May Peel) female  35     1     0
## 5                            Allen, Mr. William Henry   male  35     0     0
## 6                                    Moran, Mr. James   male  NA     0     0
##             Ticket    Fare Cabin Embarked
## 1        A/5 21171  7.2500              S
## 2         PC 17599 71.2833   C85        C
## 3 STON/O2. 3101282  7.9250              S
## 4           113803 53.1000  C123        S
## 5           373450  8.0500              S
## 6           330877  8.4583              Q

p_age = ggplot(train) +
  geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
  theme(legend.position = "right")

p_sex = ggplot(train, mapping = aes(x = Sex, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Sex') +
  scale_fill_discrete(name="Surv")

p_class = ggplot(train, mapping = aes(x = Pclass, fill = Survived, colour = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Pclass') +
  theme(legend.position = "none")

p_emb = ggplot(train, aes(Embarked, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Embarked') +
  theme(legend.position = "none")

p_sib = ggplot(train, aes(SibSp, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'SibSp') +
  theme(legend.position = "none")

p_par = ggplot(train, aes(Parch, fill = Survived)) +
  geom_bar(stat='count', position='fill') +
  labs(x = 'Parch') +
  theme(legend.position = "none")

p_fare = ggplot(train) +
  geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
  scale_x_log10() +
  theme(legend.position = "none")

p_age

## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).

p_sex

p_fare

## Warning in scale_x_log10(): log-10 transformation introduced infinite values.

## Warning: Removed 15 rows containing non-finite outside the scale range
## (`stat_bin()`).

p_class

p_emb

p_sib

p_par