In [1]: import numpy as np

import matplotlib.pyplot as plt

%matplotlib inline

In [2]: import pandas as pd

In [3]: df = pd.read_csv(r"D:\College\TE\SEM-2\Practical\DSBDA\2\AcademicPerformance.csv")

In [4]: print(df)

gender race/ethnicity parental level of education lunch \

0 female group B bachelor's degree standard
1 female group C some college standard
2 female group B master's degree standard
3 male group A associate's degree free/reduced
4 male group C some college standard
... ... ... ... ...
2235 NaN NaN NaN NaN
2236 NaN NaN NaN NaN
2237 NaN NaN NaN NaN
2238 NaN NaN NaN NaN
2239 NaN NaN NaN NaN

test preparation course Year_Birth math score reading score \

0 none 1970.0 72.0 72
1 completed 1961.0 NaN na
2 none 1958.0 90.0 95
3 none 1967.0 NaN NaN
4 none 1989.0 76.0 78
... ... ... ... ...
2235 NaN NaN NaN NaN
2236 NaN NaN NaN NaN
2237 NaN NaN NaN NaN
2238 NaN NaN NaN NaN
2239 NaN NaN NaN NaN

writing score Dt_Admission College_Fees

0 74 6/16/14 $84,835.00
1 A 6/15/14 $57,091.00
2 93 5/13/14 $67,267.00
3 44 05-11-2014 $32,474.00
4 75 04-08-2014 $21,474.00
... ... ... ...
2235 NaN NaN NaN
2236 NaN NaN NaN
2237 NaN NaN NaN
2238 NaN NaN NaN
2239 NaN NaN NaN

[2240 rows x 11 columns]

In [5]: print(df['math score'])

0 72.0
1 NaN
2 90.0
3 NaN
4 76.0
...
2235 NaN
2236 NaN
2237 NaN
2238 NaN
2239 NaN
Name: math score, Length: 2240, dtype: float64

In [6]: print(df['math score'].isnull())

0 False
1 True
2 False
3 True
4 False
...
2235 True
2236 True
2237 True
2238 True
2239 True
Name: math score, Length: 2240, dtype: bool

In [7]: print(df['reading score'])

0 72
1 na
2 95
3 NaN
4 78
...
2235 NaN
2236 NaN
2237 NaN
2238 NaN
2239 NaN
Name: reading score, Length: 2240, dtype: object

In [8]: print(df['reading score'].isnull())

0 False
1 False
2 False
3 True
4 False
...
2235 True
2236 True
2237 True
2238 True
2239 True
Name: reading score, Length: 2240, dtype: bool
In [9]: missing_values = ["n/a", "na", "--"]
df = pd.read_csv(r"D:\College\TE\SEM-2\Practical\DSBDA\2\AcademicPerformance.csv", na_v

In [10]: print(df['reading score'])

0 72.0
1 NaN
2 95.0
3 NaN
4 78.0
...
2235 NaN
2236 NaN
2237 NaN
2238 NaN
2239 NaN
Name: reading score, Length: 2240, dtype: float64

In [11]: print(df['reading score'].isnull())

0 False
1 True
2 False
3 True
4 False
...
2235 True
2236 True
2237 True
2238 True
2239 True
Name: reading score, Length: 2240, dtype: bool

In [12]: dataset = [11,41,20,3,101,55,68,97,99,6]

In [13]: sorted(dataset)

Out[13]: [3, 6, 11, 20, 41, 55, 68, 97, 99, 101]

In [14]: quantile1, quantile3 = np.percentile(dataset, [25,75])

In [15]: print(quantile1, quantile3)

13.25 89.75

In [16]: iqr_value = (quantile3 - quantile1)

In [17]: print(iqr_value)

76.5

In [18]: lower_bound_value = quantile1 - (1.5*iqr_value)

In [19]: upper_bound_value = quantile3 + (1.5*iqr_value)

In [20]: print(lower_bound_value, upper_bound_value)

-101.5 204.5

In [21]: from datetime import date

df['age'] = date.today().year - df['Year_Birth']

In [22]: df['Year'] = pd.DatetimeIndex(df['Dt_Admission']).year

df['E_L'] = date.today().year - df['Year']

In [23]: df.head(5)

Out[23]:
parental test
math reading writing
gender race/ethnicity level of lunch preparation Year_Birth Dt_Admi
score score score
education course

bachelor's
0 female group B standard none 1970.0 72.0 72.0 74 6/
degree

some
1 female group C standard completed 1961.0 NaN NaN A 6/
college

master's
2 female group B standard none 1958.0 90.0 95.0 93 5/
degree

associate's
3 male group A free/reduced none 1967.0 NaN NaN 44 05-11
degree

some
4 male group C standard none 1989.0 76.0 78.0 75 04-08
college

In [24]: df['Fees$'] = df['College_Fees'].str.replace(',', '').str.replace('$', '').str.replace(

df['Fees_M$'] = df['Fees$'].apply(lambda X:round(X/1000000))

In [25]: df.head(5)

Out[25]:
parental test
math reading writing
gender race/ethnicity level of lunch preparation Year_Birth Dt_Admi
score score score
education course

bachelor's
0 female group B standard none 1970.0 72.0 72.0 74 6/
degree

some
1 female group C standard completed 1961.0 NaN NaN A 6/
college

master's
2 female group B standard none 1958.0 90.0 95.0 93 5/
degree

associate's
3 male group A free/reduced none 1967.0 NaN NaN 44 05-11
degree

some
4 male group C standard none 1989.0 76.0 78.0 75 04-08
college

In [ ]: ​