In [2]: import pandas as pd

In [3]: iris_dataset= pd.read_csv(r"C:\Users\khush\Desktop\Iris.csv"

)

In [5]: iris_dataset
.head()

Out[5]: Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species

0 1 5.1 3.5 1.4 0.2 Iris-setosa

1 2 4.9 3.0 1.4 0.2 Iris-setosa

2 3 4.7 3.2 1.3 0.2 Iris-setosa

3 4 4.6 3.1 1.5 0.2 Iris-setosa

4 5 5.0 3.6 1.4 0.2 Iris-setosa

In [6]: iris_dataset
.describe()

Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm

Out[6]:
count 150.000000 150.000000 150.000000 150.000000 150.000000

mean 75.500000 5.843333 3.054000 3.758667 1.198667

std 43.445368 0.828066 0.433594 1.764420 0.763161

min 1.000000 4.300000 2.000000 1.000000 0.100000

25% 38.250000 5.100000 2.800000 1.600000 0.300000

50% 75.500000 5.800000 3.000000 4.350000 1.300000

75% 112.750000 6.400000 3.300000 5.100000 1.800000

max 150.000000 7.900000 4.400000 6.900000 2.500000

In [7]: iris_dataset.mean()

C:\Users\khush\AppData\Local\Temp\ipykernel_17568\906983207.py:1:
FutureWarni ng: The default value of numeric_only in DataFrame.mean is
deprecated. In a f uture version, it will default to False. In
addition, specifying 'numeric_onl y=None' is deprecated. Select only
valid columns or specify the value of nume ric_only to silence this
warning. iris_dataset.mean()

Out[7]: Id 75.500000
SepalLengthCm 5.843333
SepalWidthCm 3.054000
 PetalLengthCm 3.758667
PetalWidthCm 1.198667
dtype: float64

In [8]: iris_dataset
.median()

C:\Users\khush\AppData\Local\Temp\ipykernel_17568\543178892.py:1:
FutureWarni ng: The default value of numeric_only in DataFrame.median
is deprecated. In a future version, it will default to False. In
addition, specifying 'numeric_on ly=None' is deprecated. Select only
valid columns or specify the value of num eric_only to silence this
warning. iris_dataset.median()

Out[8]: Id 75.50
SepalLengthCm 5.80
SepalWidthCm 3.00
PetalLengthCm 4.35
PetalWidthCm 1.30
dtype: float64

In [9]: iris_dataset
.Species.mode()

Out[9]: 0 Iris-
setosa 1 Iris-
versicolor
2 Iris-virginica
Name: Species, dtype: object

In [10]: iris_dataset
.groupby(['Species']).count()

Out[10]:
Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm
Species

Iris-setosa 50 50 50 50 50

Iris-versicolor 50 50 50 50 50

Iris-virginica 50 50 50 50 50

In [11]: iris_dataset
.SepalLengthCm
.std()

Out[11]: 0.8280661279778629
[12]: iris_dataset.SepalWidthCm.std()

Out[12]: 0.4335943113621737

In [13]: iris_dataset
.PetalLengthCm
.std()

Out[13]: 1.7644204199522617
In
In [14]: iris_dataset
.PetalWidthCm
.std()

Out[14]: 0.7631607417008414

In [15]: setosa_stats= iris_dataset

[iris_dataset
['Species'
] == 'Iris-setosa'
].describe

In [16]: print("Iris-setosa statistics:"

)
print(setosa_stats
)

Iris-setosa statistics:
Id SepalLengthCm SepalWidthCm PetalLengthCm
PetalWidthCm count 50.00000 50.00000 50.000000
50.000000 50.00000 mean 25.50000 5.00600 3.418000
1.464000 0.24400 std 14.57738 0.35249 0.381024
0.173511 0.10721 min 1.00000 4.30000 2.300000
1.000000 0.10000 25% 13.25000 4.80000 3.125000
1.400000 0.20000
50% 25.50000 5.00000 3.400000 1.500000
0.20000 75% 37.75000 5.20000 3.675000 1.575000
0.30000 max 50.00000 5.80000 4.400000 1.900000
0.60000
In [17]: versicolor_stats
= iris_dataset
[iris_dataset
['Species'
] == 'Iris-versicolor'
].

In [18]: print("\nIris-versicolor statistics:"

)
print(versicolor_stats
)

Iris-versicolor statistics:
Id SepalLengthCm SepalWidthCm PetalLengthCm
PetalWidthCm count 50.00000 50.000000 50.000000
50.000000 50.000000 mean 75.50000 5.936000 2.770000
4.260000 1.326000 std 14.57738 0.516171 0.313798
0.469911 0.197753 min 51.00000 4.900000 2.000000
3.000000 1.000000 25% 63.25000 5.600000 2.525000
4.000000 1.200000
50% 75.50000 5.900000 2.800000 4.350000
1.300000 75% 87.75000 6.300000 3.000000 4.600000
1.500000 max 100.00000 7.000000 3.400000 5.100000
1.800000
In

[19]: virginica_stats = iris_dataset[iris_dataset['Species'] == 'Iris-

virginica'].de

In [20]: print("\nIris-virginica statistics:"

)
print(virginica_stats
)

Iris-virginica statistics:
Id SepalLengthCm SepalWidthCm PetalLengthCm
PetalWidthCm count 50.00000 50.00000 50.000000
50.000000 50.00000 mean 125.50000 6.58800 2.974000
5.552000 2.02600 std 14.57738 0.63588 0.322497
0.551895 0.27465 min 101.00000 4.90000 2.200000
4.500000 1.40000 25% 113.25000 6.22500 2.800000
5.100000 1.80000
50% 125.50000 6.50000 3.000000 5.550000
2.00000 75% 137.75000 6.90000 3.175000 5.875000
2.30000 max 150.00000 7.90000 3.800000 6.900000
2.50000

In [22]: setosa_data= iris_dataset

[iris_dataset
['Species'] == 'Iris-setosa'
]

In [24]: setosa_q1 = setosa_data

['SepalLengthCm'
].quantile(0.25)

In [25]: print("First Quartile (Q1) for Iris-setosa (sepal_length):"

, setosa_q1)

First Quartile (Q1) for Iris-setosa (sepal_length): 4.8

In [27]: setosa_data= iris_dataset
[iris_dataset
['Species'] == 'Iris-setosa'
]

In [28]: setosa_q3 = setosa_data

['SepalLengthCm'
].quantile(0.75)

In [29]: print("Third Quartile (Q3) for Iris-setosa (sepal_length):"

, setosa_q3)

Third Quartile (Q3) for Iris-setosa (sepal_length): 5.2

In [30]: setosa_iqr= setosa_q3- setosa_q1

In [31]: print("Interquartile Range (IQR) for Iris-setosa (sepal_length):"

, setosa_iqr
)

Interquartile Range (IQR) for Iris-setosa (sepal_length):

0.40000000000000036
In
[32]: import seaborn as sns
import matplotlib.pyplot as plt

In [34]: plt.figure(figsize=(10, 8))

sns.boxplot(x='Species', y='SepalLengthCm'
, data=iris_dataset
)
plt.title('Box Plot of Sepal Length for All Species'
)
plt.show()

In [ ]: