import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt

from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler

df= pd.read_csv('student.csv')
df.head()

	gender	ethnicity	parental_education	lunch	test_preparation_course	math_score	reading_score	writing_score
0	female	group B	bachelor's degree	standard	none	72	72	74
1	female	group C	some college	standard	completed	69	90	88
2	female	group B	master's degree	standard	none	90	95	93
3	male	group A	associate's degree	free/reduced	none	47	57	44
4	male	group C	some college	standard	none	76	78	75

#1. Upload the dataset to Google Colab and change the "test_preparation_course" into categorical variable.
df.dtypes

	0
gender	object
ethnicity	object
parental_education	object
lunch	object
test_preparation_course	object
math_score	int64
reading_score	int64
writing_score	int64

dtype: object

df['test_preparation_course'] = df['test_preparation_course'].astype('category') # how to change data types
df.dtypes

	0
gender	object
ethnicity	object
parental_education	object
lunch	object
test_preparation_course	category
math_score	int64
reading_score	int64
writing_score	int64

dtype: object

#2. Use value_counts() function to find out the how many students
#participated the "test_preparation_course" and how many did not.
df['test_preparation_course'].value_counts()

	count
test_preparation_course
none	642
completed	358

dtype: int64

#3. Let's create a data visualization by using Python.
#Create a histogram to show the distribution of "reading_score".

plt.figure(figsize=(4,3))
sns.histplot(data= df, x= 'reading_score', kde=True, color= '#d62828',
             binwidth= 5)
plt.show()

#4 Create a new data frame called df_new. In this data frame,
#you need to transform two variables (gender & test_preparation_course)
#to dummy variables and drop first columns.

df_new = pd.get_dummies(df, columns=['gender', 'test_preparation_course'],
                        dtype=int, drop_first=True)
df_new.head()

	ethnicity	parental_education	lunch	math_score	reading_score	writing_score	gender_male	test_preparation_course_none
0	group B	bachelor's degree	standard	72	72	74	0	1
1	group C	some college	standard	69	90	88	0	0
2	group B	master's degree	standard	90	95	93	0	1
3	group A	associate's degree	free/reduced	47	57	44	1	1
4	group C	some college	standard	76	78	75	1	1

!jupyter nbconvert --to html bana410_Homework1.ipynb

[NbConvertApp] Converting notebook bana410_Homework1.ipynb to html
[NbConvertApp] WARNING | Alternative text is missing on 1 image(s).
[NbConvertApp] Writing 323039 bytes to bana410_Homework1.html