holman57

import pandas as pd

education = pd.DataFrame({'Age': [5, 23, 16, 33, 78, 15, 41, 66]})
bins = [0, 13, 19, 60, 100]
labels = ['Elementary', 'High School', 'Adult', 'Senior']
education['Age Group'] = pd.cut(education['Age'], bins=bins, labels=labels)

print(education)
# Once the pd.cut() function has been applied, the original column will be replaced with a new column 
# containing the bin labels. The bin labels are integers representing the bin that each value fell into.

holman57

#!/bin/bash
if [ $# -eq 0 ]
then
	echo -e "You need to specify the target domain.\n"
	echo -e "Usage:"
	echo -e "\t$0 <domain>"
	exit 1
else
	domain=$1
fi

holman57

import pandas as pd
planets = pd.DataFrame({
    "Planet": ["Mercury", "Venus", "Earth", "Mars", "Jupiter", "Saturn"],
    "Distance_AU": [0.39, 0.72, 1, 1.52, 5.20, 9.58]
})
dist = planets['Distance_AU']
planets['dist_norm_z_score'] = (dist - dist.mean()) / dist.std()
# x_new = (x - x_min) / (x_max - x_min)
planets['dist_norm_min_max'] = (dist - dist.min()) / (dist.max() - dist.min())
print(planets)

holman57

#!/bin/bash
if [ $# -eq 0 ]
then
	echo -e "You need to specify the target domain.\n"
	echo -e "Usage:"
	echo -e "\t$0 <domain>"
	exit 1
else
	domain=$1
fi

holman57

import pandas as pd
df1 = pd.DataFrame(columns=['a', 'b', 'c', 'd', 'e'])
df1.loc[0] = pd.Series({'a': "α", 'b': "β", 'c': "γ", 'd': "δ", 'e': "ε"})
df1.loc[1] = pd.Series({'a': "ζ", 'b': "η", 'c': "θ", 'd': "ι", 'e': "κ"})
df1.loc[2] = pd.Series({'a': "λ", 'b': "μ", 'c': "ν", 'd': "ξ", 'e': "ο"})
df1.loc[3] = pd.Series({'a': "π", 'b': "ρ", 'c': "σ", 'd': "τ", 'e': "υ"})
df1.loc[4] = pd.Series({'a': "φ", 'b': "χ", 'c': "ψ", 'd': "ω", 'e': "Ω"})
df2 = pd.DataFrame(columns=['a', 'b', 'c', 'd', 'e'])
df2.loc[0] = pd.Series({'a': "α", 'b': "β", 'c': "γ", 'd': "δ", 'e': "ε"})
df2.loc[1] = pd.Series({'a': "ζ", 'b': "η", 'c': "charlie", 'd': "ι", 'e': "κ"})

holman57

# Lead and Lag in SQL Server
SELECT
	[SalesOrderID]
	,[OrderDate]
	,[CustomerID]
	,[TotalDue]
	,[NextTotalDue] = LEAD([TotalDue], 1) OVER(PARTITION BY [CustomerID] ORDER BY [SalesOrderID])
	,[PrevTotalDue] = LAG([TotalDue], 1) OVER(PARTITION BY [CustomerID] ORDER BY [SalesOrderID])
FROM [AdventureWorks2019].[Sales].[SalesOrderHeader]
ORDER BY [SalesOrderID]

holman57

cursor = conn.cursor()
fetchall_cnt = 0
for oven in all_ovens:
	oven_id = oven[0]
	sql_string = "SELECT * FROM product_orders WHERE product_id = %s"
	cursor.execute(sql_string, [oven_id])
	oven_order = cursor.fetchall()
	fetchall_cnt += 1
	print(oven_order, "/n")
	print("fetchall_cnt:", fetchall_cnt)

holman57

# Generate Random Samples using Numpy Random Normal Distirubtion
μ, σ = 0, 0.1
x = np.random.normal(μ, σ, 1000)
print(abs(μ - np.mean(x)))
print(abs(σ - np.std(x, ddof=1)))
import matplotlib.pyplot as plt
count, bins, ignored = plt.hist(x, 30, density=True)
plt.plot(bins, 1/(σ * np.sqrt(2 * np.pi)) * np.exp(-(bins - μ)**2 / (2 * σ**2)), linewidth=2, color='r')
plt.show()
print(np.random.normal(3, 2.5, size=(2, 4)))

holman57

-- Examples of JOIN ON in MS SQL Server
-- JOIN ON DATEDIFF
SELECT w2.[id] AS [ID]
FROM Weather AS w1
JOIN Weather AS w2 
    ON DATEDIFF(DAY, w1.[recordDate], w2.[recordDate]) = 1
WHERE w2.[temperature] > w1.[temperature]
;
-- JOIN ON DATEADD
SELECT w1.[id] AS [ID] 

holman57

# Interfacing with environment variables in Python
import os
os.environ["USERNAME"] = "new-user"
os.environ["PASSWORD"] = "new-password"
print(os.environ["USERNAME"])
print(os.environ["PASSWORD"])
print(os.environ["PATH"])
# Retrieving the value of an environment variable with a default value
database_url = os.environ.get("DATABASE_URL", "localhost:5432")
print(database_url)