# A$$klay$$c$$ dosya olan 'agaricus$-$lepiota.names' dosyas$$n$$ okuyarak i$$eri$$ine bak$$yoruz$.$

file$\_$path $=$ 'agaricus$-$lepiota.names'

# Dosyan$$n i$$eri$$ini okuma

with open$($file$\_$path, $\text{'}$r$\text{'})$ as file:

names$\_$content $=$ file.read$()$

# $$eri$$in ilk $10000$ karakterini g$$stermek i$$in k$$saltma yaparak i$$eri$$i g$$sterelim

print$($names$\_$content$[$:$10000])$ # $$lk $10000$ karakteri g$$steriyoruz$.$

#$\%\%$

import pandas as pd

# Veri setini okuyarak DataFrame olu$$turma

data$\_$file$\_$path $=$ 'agaricus$-$lepiota.data.csv$\text{'}$

column$\_$names $=[\text{'}$class$\text{'},$ 'cap$-$shape', 'cap$-$surface', 'cap$-$color', 'bruises', 'odor',

'gill$-$attachment', 'gill$-$spacing', 'gill$-$size', 'gill$-$color',

'stalk$-$shape', 'stalk$-$root', 'stalk$-$surface$-$above$-$ring',

'stalk$-$surface$-$below$-$ring', 'stalk$-$color$-$above$-$ring',

'stalk$-$color$-$below$-$ring', 'veil$-$type', 'veil$-$color', 'ring$-$number',

'ring$-$type', 'spore$-$print$-$color', 'population', 'habitat'$]$

mushroom$\_$data $=$ pd$.$read$\_$csv$($data$\_$file$\_$path, header$=$None, names$=$column$\_$names$)$

# $$lk $5$ sat$$r$$ g$$stererek veri yap$$s$$n$$ inceleyelim

mushroom$\_$data.head$()$

#$\%\%$

print$($mushroom$\_$data.describe$())$

#$\%\%$

mushroom$\_$data.info$()$

#All features are categorical but given as 'object' type. First, it is converted into 'category' type.

#$\%\%$

from plotly.subplots import make$\_$subplots

import plotly.graph$\_$objects as go

specs $=[[\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\}],[\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\}],[\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\}],[\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\}],[\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\},\{\text{'}$type$\text{'}$:'domain'$\}]]$

fig $=$ make$\_$subplots$($rows$=5,$ cols$=5,$ specs$=$specs$)$

a$=1$

b$=1$

xx$=-0\mathrm{.}172$

yy$=1\mathrm{.}267$

l$=[]$

for col in mushroom$\_$data.columns:

fig.add$\_$trace$($go$.$Pie$($labels$=[$n for n in mushroom$\_$data$[$col$].$value$\_$counts$().$index$],$ values$=[$v for v in mushroom$\_$data$[$col$].$value$\_$counts$()*100/$sum$($mushroom$\_$data$[$col$].$value$\_$counts$())],$ name$=$col$),$

a$,$ b$)$

l$.$append$($dict$($text$=$col, x$=$xx$+(0\mathrm{.}225*$b$),$ y$=$yy$-(0\mathrm{.}222*$a$),$ font$\_$size$=10,$ showarrow$=$False$))$

a$+=1$

if a$>5$:

a$=1$

b$+=1$

fig.update$($layout$\_$title$\_$text$=$'Features',

layout$\_$showlegend$=$False$)$

fig.update$\_$layout$($

title$\_$font$\_$family$=$"Arial",

title$\_$font$\_$size$=25,$

annotations$=$l$)$

fig.update$\_$traces$($hole$=\mathrm{.}4,$ hoverinfo$=$"label$+$percent$+$name",textinfo$=$'none'$)$

fig.show$()$

#$\%\%$

def make$\_$categorical$($mushroom$\_$data, columns$)$:

for column in columns:

mushroom$\_$data$[$column$]=$ pd$.$Categorical$($mushroom$\_$data$[$column$])$

return mushroom$\_$data

#$\%\%$

columns $=$ mushroom$\_$data.columns

data $=$ make$\_$categorical$($mushroom$\_$data, columns$)$

#$\%\%$

mushroom$\_$data.info$()$

#$\%\%$

mushroom$\_$data.shape

#There $8124$ observation and $23$ features in mushroom dataset.

#$\%\%$

mushroom$\_$data.isnull$().$any$()$

#There is no missing value in mushroom dataset.

#$\%\%$

# Veri t$$rleri incelemesi

data$\_$types $=$ mushroom$\_$data.dtypes

data$\_$types

#$\%\%$

mushroom$\_$data$\_$habitat $=$ mushroom$\_$data$[\text{'}$habitat$\text{'}].$groupby$($mushroom$\_$data$[\text{'}$class$\text{'}]).$value$\_$counts$($normalize$=$ True$).$rename$(\text{'}$frequency$\text{'}).$to$\_$frame$().$reset$\_$index$()$

mushroom$\_$data$\_$habitat

#$\%\%$

from matplotlib import pyplot as plt

import seaborn as sns

# Let$`$s create a bar plot to show the Habitat Distribution

sns$.$barplot$($data $=$ mushroom$\_$data$\_$habitat,x$=$'habitat',y$=$'frequency',hue$=$'class'$)$

plt$.$xlabel$(\text{'}$Habitat$\text{'})$

plt$.$ylabel$(\text{'}$frequenncy$(\%)\text{'})$

plt$.$title$("$Habitat Distribution: Edible Vs Poisonous"$)$;

#$\%\%$

mushroom$\_$data$\_$popu $=$ mushroom$\_$data$[\text{'}$population$\text{'}].$groupby$($mushroom$\_$data$[\text{'}$class$\text{'}]).$value$\_$counts$($normalize$=$ True$).$rename$(\text{'}$frequency$\text{'}).$to$\_$frame$().$reset$\_$index$()$

mushroom$\_$data$\_$popu

#$\%\%$

## Let$`$s create a bar plot to show the population: Edible Vs Poisonous

import plotly.express as px

fig $=$ px$.$bar$($data$\_$frame$=$ mushroom$\_$data$\_$popu $,$ x$=$ 'population', y$=$ 'frequency',color$=$ 'class', barmode$=$ 'group', title$=$'population: Edible Vs Poisonous'$)$

fig.update$\_$layout$($xaxis$\_$title$=$ 'population' $,$ yaxis$\_$title$=$ 'frequenncy$(\%)\text{'})$

#$\%\%$

ring$\_$num $=\{$

$\text{'}$o$\text{'}$: $1,$

$\text{'}$t$\text{'}$: $2,$

$\text{'}$n$\text{'}$:$0$

$\}$

ring$\_$num

mushroom$\_$data$\_$ring $=$ mushroom$\_$data$[\text{'}$ring$-$number'$].$replace$($ring$\_$num$).$groupby$($mushroom$\_$data$[\text{'}$class$\text{'}]).$value$\_$counts$($normalize$=$ True$).$rename$(\text{'}$frequency$\text{'}).$to$\_$frame$().$reset$\_$index$()$

mushroom$\_$data$\_$ring

#$\%\%$

#Let$`$s create a barchart to visualize the number of rings in each class

fig $=$ px$.$bar$($data$\_$frame$=$ mushroom$\_$data$\_$ring $,$ x $=$ 'ring$-$number' $,$ y$=$ 'frequency' $,$ color $=$ 'class' $,$ barmode$=$ 'group',title$=$ 'Number of rings: Edible Vs Poisonous'$)$

fig.update$\_$layout$($xaxis$\_$title$=$ 'number of rings' $,$ yaxis$\_$title $=$ 'frequency $(\%)\text{'})$ THE PYTHON CODE GIVEN ABOVE IS RELATED TO RANDOM FOREST CLASSIFICATION IN THE DATA SCIENCE COURSE.

PLEASE INTERPRET THIS CODE AND PREPARE A REPORT ACCORDING TO THE SUBJECTS AND CODES.