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

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

	ID	TV	Radio	Newspaper	Sales
0	1	230.1	37.8	69.2	22.1
1	2	44.5	39.3	45.1	10.4
2	3	17.2	45.9	69.3	9.3
3	4	151.5	41.3	58.5	18.5
4	5	180.8	12.8	58.4	12.9

#1.

plt.figure(figsize=(10,5))
sns.histplot(data= df, x='Sales', color='lightgreen', kde=True,
             fill=False, binwidth= 5)
plt.show()

#majority of the distrribution is around 10 to 15 sales

2.
plt.figure(figsize=(8,4))
sns.jointplot(data=df, x='TV', y='Radio', kind='reg')
plt.show()

<Figure size 800x400 with 0 Axes>

#we found that there is no relaitonship between Tv and Radio sales

#3.
plt.figure(figsize=(8,4))
sns.jointplot(data=df, x='TV', y='Sales', kind='reg')
plt.show()

<Figure size 800x400 with 0 Axes>

# we found a postive realtionship between TV and Sales

#4.
plt.figure(figsize=(8,4))
sns.jointplot(data=df, x='Newspaper', y='Sales', kind='reg')
plt.show()

<Figure size 800x400 with 0 Axes>

#we found a positive relationship between Newspaper and Sales

# hw 2 &3

df2 = pd.read_csv('energy.csv')
df2.head()

	Date	commercial	industrial
0	1/1/01	629	13128
1	2/1/01	548	11421
2	3/1/01	553	12454
3	4/1/01	550	11674
4	5/1/01	575	11751

df2.dtypes

	0
Date	object
commercial	int64
industrial	int64

dtype: object

df2['Date']=pd.to_datetime(df2['Date'])
df2.head()

/tmp/ipython-input-321837906.py:1: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  df2['Date']=pd.to_datetime(df2['Date'])

	Date	commercial	industrial
0	2001-01-01	629	13128
1	2001-02-01	548	11421
2	2001-03-01	553	12454
3	2001-04-01	550	11674
4	2001-05-01	575	11751

#1
plt.figure(figsize=(12,5))
sns.lineplot(data= df2, x='Date',y='commercial', linestyle='--', markersize='8',
             marker='o', color='limegreen', mfc='orange', mec='yellow', label='comm')
#sns.lineplot(data=df, x='Date',y='Platinum', linestyle='--', markersize='12',
 #            marker='x', color='teal', mfc='black', mec='steelblue', label='platinum')
plt.show()

#this visual shows commercial energy generation over time

#2
plt.figure(figsize=(12,5))
sns.lineplot(data= df2, x='Date',y='commercial', linestyle='--', markersize='8',
             marker='o', color='limegreen', mfc='orange', mec='yellow', label='comm')
sns.lineplot(data=df2, x='Date',y='industrial', linestyle='--', markersize='12',
            marker='x', color='teal', mfc='black', mec='steelblue', label='platinum')
plt.show()

#this visual shows commercial and industrial energy generation over time

#3
def func_(x):
  outcome= x**3 + 2 * x**2 + 12
  return outcome

#4
x = np.linspace(1,10,100)
y = func_(x)

plt.figure(figsize=(4, 4))
plt.plot(x, y, color='indigo', linestyle='--', linewidth=3)
#plt.title('Cubic Function')
plt.xlabel('x')
plt.ylabel('y')
plt.grid()
plt.show()

df3 = pd.read_csv('customer.csv')
df3.head()

	Education	Income	Kidhome	Marital_Status	Recency	MntFruits	MntMeatProducts	NumStorePurchases	NumWebPurchases	NumWebVisitsMonth
0	Graduation	58138.0	0	Single	58	88	546	4	8	7
1	Graduation	46344.0	1	Single	38	1	6	2	1	5
2	Graduation	71613.0	0	Together	26	49	127	10	8	4
3	Graduation	26646.0	1	Together	26	4	20	4	2	6
4	PhD	58293.0	1	Married	94	43	118	6	5	5

#1.
sns.countplot(data=df3, x='Education', hue= 'Education')
plt.xticks(rotation=20)
plt.show()

# most of the customers have a college degree

#2
sns.catplot(data=df3, y='Income', x='Kidhome', kind= 'box', hue= 'Kidhome')
plt.xticks(rotation=20)
plt.show()

# we found that if you have less kids, you have a higher income

#3
plt.figure(figsize=(8,4))
sns.jointplot(data=df3, x='NumStorePurchases', y='NumWebPurchases', kind='reg')
plt.show()

<Figure size 800x400 with 0 Axes>

# they have a positive relationship

#4
sns.kdeplot(data=df3, x='Income', hue='Marital_Status', common_norm=False)
plt.show()

sns.catplot(data=df3, y='Income', x='Marital_Status', kind= 'box', hue= 'Marital_Status')
plt.xticks(rotation=20)
plt.show()

#people who are single have a higher income, people who are alone tend to have the lowest income

#5
sns.catplot(data=df3, y='Income', x='Education', kind= 'box', hue= 'Education')
plt.xticks(rotation=20)
plt.show()

# on average people with Masters and PHDs tend to have the higher incomes compared to other education levels