Data Analyst
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, unionlibrary('tidyr')
library('readr')
library('stringr')
library('forcats')
library('modelr')Material Praktikum
Lorem ipsum dolor sit amet. Sit similique omnis a quam nihil aut inventore ipsum in rerum internos. Qui voluptatem iusto hic odit deserunt est deserunt vero eos voluptate omnis At dolor repudiandae sed cupiditate porro. Et consectetur eaque aut iste officia a omnis animi.
library(ggplot2)
netflix <- read.csv("netflix_titles.csv")
custom_col <- c("#776B5D", "#B0A695", "#EBE3D5")
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,
tittle = "Pie Chart of Netflix shows") +
coord_polar(theta = "y", start = 0) +
scale_fill_manual(values = custom_col)
ggplot(netflix, aes(x = "", fill = factor(type))) +
geom_bar(width = 1) +
scale_fill_manual(values = custom_col)
pie
Data Analyst Train Information
Lorem ipsum dolor sit amet. Sit similique omnis a quam nihil aut inventore ipsum in rerum internos. Qui voluptatem iusto hic odit deserunt est deserunt vero eos voluptate omnis At dolor repudiandae sed cupiditate porro. Et consectetur eaque aut iste officia a omnis animi.
train <- read.csv("train (1).csv")
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 Qtrain <- train %>% mutate(
Survived = factor(Survived),
Pclass = factor(Pclass),
Embarked = factor(Embarked),
Sex = factor(Sex)
)
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 Qsummary(train)## PassengerId Survived Pclass Name Sex
## Min. : 1.0 0:549 1:216 Length:891 female:314
## 1st Qu.:223.5 1:342 2:184 Class :character male :577
## Median :446.0 3:491 Mode :character
## Mean :446.0
## 3rd Qu.:668.5
## Max. :891.0
##
## Age SibSp Parch Ticket
## Min. : 0.42 Min. :0.000 Min. :0.0000 Length:891
## 1st Qu.:20.12 1st Qu.:0.000 1st Qu.:0.0000 Class :character
## Median :28.00 Median :0.000 Median :0.0000 Mode :character
## Mean :29.70 Mean :0.523 Mean :0.3816
## 3rd Qu.:38.00 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :80.00 Max. :8.000 Max. :6.0000
## NA's :177
## Fare Cabin Embarked
## Min. : 0.00 Length:891 : 2
## 1st Qu.: 7.91 Class :character C:168
## Median : 14.45 Mode :character Q: 77
## Mean : 32.20 S:644
## 3rd Qu.: 31.00
## Max. :512.33
## custom_col <- c("#776B5D", "#B0A695", "#EBE3D5")
ggplot(train, aes(x = "", fill = factor(Pclass))) +
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,
tittle = "Pie Chart of P") + coord_polar(theta = "y", start = 0) +
scale_fill_manual(values = custom_col)
p_age = ggplot(train) +
geom_freqpoly(mapping = aes(x = Age, color = Survived), binwidth = 1) +
theme(legend.position = "right") +
scale_fill_manual(values = custom_col)
p_sex = ggplot(train, mapping = aes(x = Sex, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Sex') +
scale_fill_manual(values = custom_col)
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") +
scale_fill_manual(values = custom_col)
p_emb = ggplot(train, aes(Embarked, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Embarked') +
theme(legend.position = "none")+
scale_fill_manual(values = custom_col)
p_sib = ggplot(train, aes(SibSp, fill = Survived)) +
geom_bar(stat='count', position = 'fill') +
labs(x = 'SibSp') +
theme(legend.position = "none") +
scale_fill_manual(values = custom_col)
p_par = ggplot(train, aes(Parch, fill = Survived)) +
geom_bar(stat='count', position='fill') +
labs(x = 'Parch') +
theme(legend.position = "none") +
scale_fill_manual(values = custom_col)
p_fare = ggplot(train) +
geom_freqpoly(mapping = aes(Fare, color = Survived), binwidth = 0.05) +
scale_x_log10() +
theme(legend.position = "none") +
scale_fill_manual(values = custom_col)
p_age
Fig. 2
p_sex
Fig. 2
p_fare
Fig. 2
p_class
Fig. 2
p_emb
Fig. 2
p_sib
Fig. 2
p_par
Fig. 2