Learning Task: upload data to colab and read data python exploratory analysis

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

#read data
df = pd.read_csv('student.csv')
df.head(10) #deafult is 5, we put in 10 to see top 10 rows if data.. df.tail() to see last rows of data

	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
5	female	group B	associate's degree	standard	none	71	83	78
6	female	group B	some college	standard	completed	88	95	92
7	male	group B	some college	free/reduced	none	40	43	39
8	male	group D	high school	free/reduced	completed	64	64	67
9	female	group B	high school	free/reduced	none	38	60	50

# check out the data type for each column
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

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

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

dtype: object

#changing more than one datatype at a time. you need double brackets
df[['math_score', 'reading_score', 'writing_score']] = df[['math_score', 'reading_score', 'writing_score']].astype(float)
df.dtypes

	0
gender	object
ethnicity	object
parental_education	category
lunch	object
test_preparation_course	object
math_score	float64
reading_score	float64
writing_score	float64

dtype: object

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	72.0	72.0	74.0
1	female	group C	some college	standard	completed	69.0	90.0	88.0
2	female	group B	master's degree	standard	none	90.0	95.0	93.0
3	male	group A	associate's degree	free/reduced	none	47.0	57.0	44.0
4	male	group C	some college	standard	none	76.0	78.0	75.0

#counts the number of rows, not including the header
len(df)

1000

#check how many classes/label are within 'parental_education'
df['parental_education'].value_counts()

	count
parental_education
some college	226
associate's degree	222
high school	196
some high school	179
bachelor's degree	118
master's degree	59

dtype: int64

#create a visual to better explore the data distribution
sns.countplot(data= df, x= 'parental_education', hue= 'parental_education')
plt.xticks(rotation= 20) #bends the bottom names
plt.show()

#explore the distribution of scores across gender
sns.scatterplot(data=df, x='reading_score', y= 'math_score', hue = 'gender') #look at correlation
sns.kdeplot(data=df, x='reading_score', y='math_score', hue= 'gender',
            levels=4)
plt.show()