KamiBG

#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
import numpy as np

KamiBG

import pandas as pd
from matplotlib import pyplot as plt

healthcare = pd.read_csv("healthcare.csv")
print(healthcare.head())
#print(healthcare["DRG Definition"].unique())

chest_pain = healthcare[healthcare['DRG Definition'] == '313 - CHEST PAIN']
# boxplot for Alabama:
alabama_chest_pain = chest_pain[chest_pain['Provider State'] == 'AL']

KamiBG

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

data = pd.read_csv("country_data.csv")
#print(data.head())
life_expectancy = data['Life Expectancy']

# Find the Quantiles:
life_expectancy_quartiles = np.quantile(life_expectancy, [0.25, 0.5, 0.75])

KamiBG

SELECT * FROM stream
LIMIT 20;

SELECT * FROM chat
LIMIT 20;

-- What are the unique games in the stream table?
SELECT DISTINCT game FROM stream
WHERE game is NOT NULL;

KamiBG

import codecademylib3_seaborn
from matplotlib import pyplot as plt
import pandas as pd
import seaborn as sns

df = pd.read_csv('WorldCupMatches.csv')
print(df.head())

# Create a column with the total number of goals scored in each match
df['Total Goals'] = df['Home Team Goals'] + df['Away Team Goals']

KamiBG

import pandas as pd
import matplotlib.pyplot as plt

# load rankings data:
GTAW_wood = pd.read_csv('Golden_Ticket_Award_Winners_Wood.csv')
print(GTAW_wood.head())
GTAW_steel = pd.read_csv('Golden_Ticket_Award_Winners_Steel.csv')
print(GTAW_steel.head())

# write function to plot rankings over time for 1 roller coaster:

KamiBG

import pandas as pd

visits = pd.read_csv('visits.csv',
                     parse_dates=[1])
print(visits.head())
cart = pd.read_csv('cart.csv',
                   parse_dates=[1])
print(cart.head())
checkout = pd.read_csv('checkout.csv',
                       parse_dates=[1])

KamiBG

import pandas as pd

ad_clicks = pd.read_csv('ad_clicks.csv')
print(ad_clicks.head())

# Your manager wants to know which ad platform is getting you the most views. How many views (i.e., rows of the table) came from each utm_source?
views = ad_clicks.groupby('utm_source').user_id.count().reset_index().rename(columns = {'user_id': 'views'})
print(views)

# Create a new column called is_click, which is True if ad_click_timestamp is not null and False otherwise.

KamiBG

SELECT * FROM page_visits
LIMIT 20;

SELECT DISTINCT utm_campaign FROM page_visits;
SELECT DISTINCT utm_source FROM page_visits;

-- Which source is used for each campaign?
SELECT DISTINCT utm_campaign, utm_source FROM page_visits;

-- What pages are on the CoolTShirts website?

KamiBG

-- Four months into launching Codeflix, management asks you to look into subscription churn rates. It’s early on in the business and people are excited to know how the company is doing.
-- The marketing department is particularly interested in how the churn compares between two segments of users. They provide you with a dataset containing subscription data for users who were acquired through two distinct channels.
-- The dataset provided to you contains one SQL table, subscriptions. Within the table, there are 4 columns:
-- id - the subscription id
-- subscription_start - the start date of the subscription
-- subscription_end - the end date of the subscription
--segment - this identifies which segment the subscription owner belongs to
-- Codeflix requires a minimum subscription length of 31 days, so a user can never start and end their subscription in the same month.
 
 SELECT * FROM subscriptions