import pandas as pd #reads the csv data
import matplotlib.pyplot as plt #data visualization
import seaborn as sns #more data visualization

#read data
df = pd.read_csv('student.csv')
df.head(3) #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

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

1000

#create a subset from df
sample_df= df.iloc[0:200, :] # 200 rows, and all columns
len(sample_df)

200

#distribution between gender
sns.countplot(data= df, x= 'gender', hue= 'gender')
plt.show()

#another way to do the samd thing
sns.catplot(data=df, x='gender', kind= 'count', hue='gender')
plt.show()

#investigate how math score is distributed across gender
sns.catplot(data= df, x='gender', y='math_score', kind= 'bar', hue= 'lunch',
            palette={'standard':'green', 'free/reduced': 'lightgreen'}) #palette changes the colors you want to use
plt.show()

#python easteregg
sns.dogplot()