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

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

#create our first histogram
#explore how math score is distributed over entire students
plt.figure(figsize=(4,3))
sns.histplot(data= df, x= 'math_score', kde=True, color= '#d62828',
             binwidth= 10, fill= False)# fill= flase takes away the inside color of the bars
plt.show()

#countplot is to count 1 category
#catplot is to compare 2 categories

#As a data scientist, if you want to determine which
#parental_education group has the highest average
#reading score, which visualization would you use

plt.figure(figsize=(5,4))
sns.catplot(data= df, x= 'parental_education', y= 'reading_score', kind= 'bar',
            hue= 'parental_education')
plt.xticks(rotation=20)
plt.show()

<Figure size 500x400 with 0 Axes>

#If you want to determine which parental_education group
#has the largest number of students, which visualization
#would you use

plt.figure(figsize=(5,4))
sns.countplot(data= df, x= 'parental_education', hue='parental_education')
plt.xticks(rotation=20)
plt.show()

#If you want to explore how reading score spread, which
#visualization would you use?

#create our first histogram
#explore how math score is distributed over entire students
plt.figure(figsize=(4,3))
sns.histplot(data= df, x= 'reading_score', kde=True, color= '#d62828',
             binwidth= 5)
plt.show()