#numeric variable data visualization

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

#histplot
plt.figure(figsize=(10,5))
sns.histplot(data= df, x='math_score', color='lightgreen', kde=True,
             fill=False, binwidth= 5)
plt.title('Math Score Distribution')
plt.xlabel('Math Score')
plt.show()

#kdeplot: a smoother version of histogram
plt.figure(figsize=(10,5))
sns.kdeplot(data= df, x='math_score', color='green', fill=True,
            alpha= 0.1, linewidth=2, linestyle= '--')#alpha is the transperancy from a range of 0 to 1
plt.title('Math Score Distribution')
plt.xlabel('Math Score')
plt.show()

# math_score distribution across gender
plt.figure(figsize=(4,3))
sns.histplot(data= df, x='math_score', hue='gender', kde=True,
             fill=False, binwidth= 5,
             palette={'female':'lightpink', 'male':'lightblue'})
plt.title('Math Score Distribution')
plt.xlabel('Math Score')
plt.show()

plt.figure(figsize=(4,3))
sns.kdeplot(data= df, x='math_score', hue='gender', fill=True,
             alpha= 0.2, linewidth=2, linestyle= '-', common_norm=False,
             palette={'female':'lightpink', 'male':'lightblue'})
plt.title('Math Score Distribution')
plt.xlabel('Math Score')
plt.show()
#common_norm=False separates the data into independant datasets,
#True combines them

#explore the math distribution across test_preparation_course

plt.figure(figsize=(5,3))
sns.histplot(data= df, x='math_score', hue='test_preparation_course', kde=True,
             fill=True, binwidth= 5,
             palette={'none':'grey', 'completed':'purple'},
             element='step')
plt.show()

plt.figure(figsize=(5,3))
sns.kdeplot(data= df, x='math_score', hue='test_preparation_course', fill=True,
             alpha= 0.1, linewidth=1, linestyle= '-', common_norm=False,
             palette={'none':'grey', 'completed':'purple'})
plt.show()

# how math score spread across ethnicity

plt.figure(figsize=(5,3))
sns.kdeplot(data=df, x='math_score', hue='ethnicity', fill=True,
            alpha=0.2, linewidth=1, linestyle='-', common_norm=False)
plt.show()

#Summary- numeric data visualization
#1. histogram (histplot)
#2. kdeplot
#3. boxplot

#boxplot- distribution of math score

plt.figure(figsize=(5,3))
sns.boxplot(data=df, x='math_score', color='lightgreen')
plt.show()

#math score distribution across lunch

sns.catplot(data=df, y='math_score', x='lunch', kind= 'box', hue= 'lunch')
plt.show()

sns.catplot(data=df, y='math_score', x='parental_education', kind= 'box', hue= 'parental_education')
plt.xticks(rotation=20)
plt.show()

# scatterplot - two different numeric variables

plt.figure(figsize=(6,5))
sns.scatterplot(data=df, y='math_score', x='reading_score', hue='gender',
                palette={'female':'lightpink', 'male':'lightblue'}, marker='x', s=50)
plt.show()