Question 5 IRIS ?ython for Data Science - Perform Data Visualization on Iris Dataset a)Load the Titanic dataset into one of the data structures (NumPy or Fandas). )Display header rows and description of the loaded dataset. ©) Clean the data if applicable d) Find the average petal width of each category of IRIS Species @) Data Visualization for: (i) How many flowers of each species exists for each value of sepal width (i) How many flowers are there whose petal width is <1, between 1 to 2 and >2 (i) Tally the Iris-Versicolour and Iris-Virginica species according to the value of Sepal Width Click here to download dataset fnumpy - Deals multi-dimensional arrays and matrices aseaborn - Deals with data visualization ‘matplotlib - Plotting; pyplot-interactive plotting pandas - data structures and data analysis tools import seaborn as sns import pandas as pd import matplotiib.pyplot as plot a#Import csv file into variable (dataframe) Aris df = pd.read_csv(‘iris.csv') iris df.head() Sepal_Length Sepal Width Petal_Length Petal Width Class 0 35 14 02 Iris-setosa 1 49 30 14 012 Iris-setosa 2 47 32 13 0.2 ris-setosa 3 46 34 15 012 ris-setosa 4 5c 36 14 0.2 Iris-setosa print info about datafrane print("This is info() output\n") print (inis_df.info()) print("\nthis is describe() output\n") print (iris_df.describe())This is info() output RangeIndex: 150 entries, @ to 148 bata columns (total § columns) Non-Nul1 Count Dtype # Column 2 Sepal_tength 1 Sepal_width 2 Petal_tength 3 Petal_width 4 Class 150 150 150 150 150 non-null non-null non-null non-null non-null dtypes: floate4(4), object(1) memory usag None 6.0+ KB This is describer() output Sepal_Length count 150. mean std min 25% 50%, 75% max drop sepal_U Anis_d#.drop(['Sepal_Length’ ), axis=1, inplace=True) inis_d*.head( 200000 843333 828066 - 300800 108000 800000 408600 902800 ‘ength ) se u spal_Width 50.600000 054000, 433594 208000 800000 208000 308000 408000 PeuNvew Floated Floate4 floated Floated object Petal_Length 150.000000 758667 764426 00000 600000 350000 100008 -980008 One EEY Sepal Width Petal Length Petal Width Class ° 35 1 30 2 32 3 3, 4 36 14 14 13 15 14 02 tis-setosa 02. tis-setosa 02. tis-setosa 02. tis-setosa 02. tis-setosa Petal_width 150 200000 -198667 -763161 100000 -308000 300008 800000 500000 inis_df.groupby( ‘Class’ ,as_index=False)[' Petal_Width" ].mean() Class 0 ris-setose 1 ris-versicolor 2 ris-virginice Petal Width 9244 1326 2.026 # we increase the size of output graph plot. Figure(figsize=[12,6])

‘plot graph of class vs sepalwidth ax=sns.countplot (data=iris_df,x=" Sepal_width’ hue= "Class", palette="Set1") ax.set(title='Flower of each species’ ,xlabel="Sepal Width" ,ylabel='No. of flowers") plot.tight_layout() plot .show() Flower of each species lass mm ris-setosa lm Iris-versicolor mE Iris-virginica No. of flowers 2.0 2.22.3 2.42.5 2.6 2.72.8 2.93.0 3.13.2 333.435 3.63.73.83.9404.14244 Sepal Width Cut petal width accoding to interval and give Labels from categories interval = (0,1,2,4) category = ["<1','1 to 2","22'] Anis_df['Petal_catg') = pd.cut(iris_df[' Petal_Width' ), interval, labels=category) ax = sns.countplot(data = iris df,x = 'Petal_catg' ,hue='Class' ,palette='seti') ax.set(title='Petal Width’, xlabel='Category of Petals’ ,ylabel='No. of flowers") plot.show()Petal Width 50 Class lm Iris-setosa lm ris-versicolor 0 mE Iris-virginica % 30 & 2 2 20 10 o <1 ax = sns.countplot (data 1to2 Category of Petals iris_df[iris_df[ ‘Class’ >2 "Inis-setosa’],x = * Sepal_widt ax.set(title='Versicolor vs virginica’ ,xlabel="Sepal Width’ ,ylabel='No. of flowers’ plot.show()No. of flowers 2 10 © a Versicolor vs virginica Class lm iris-versicolor Mm ris-virginica 20 22 2.3 2.4 25 26 27 2829 3031 32 33 34 36 38 Sepal Width