CentralTendency

# Create a dataframe
import pandas as pd 
df_1=read_csv.('file_name')
df_1=pd.read_excel('state_naicssector_2010.xls', skiprows=4)

#list column names
list(df_1)

#Get all rows for Texas
df_2=df_1.loc[df_1['STATE DESCRIPTION']=='Texas']

#Get row at index location 7973 
df_2.loc[7973]
#Get first row in datatframe
df_2.iloc[0]

#Get all rows in a particular industry
df_2=df_1.loc[df_1['NAICS DESCRIPTION']=='Agriculture, forestry, fishing and hunting']

#Get all rows with totals for a state
df_3=df_2.loc[df_2['ENTERPRISE EMPLOYMENT SIZE']=='1:   Total']

df_3.mode(axis=1)

df_3["NUMBER OF FIRMS"].mode()

df_3["NUMBER OF FIRMS"].median()
df_3['ANNUAL PAYROLL ($1,000)'].median()

###For wednesday 
Census data 
Take a census table 
import pandas as pd
df_1=pd.read_csv('TABLE_FILE_NAME')
df_1=pd.read_csv('TABLE_FILE_NAME', skiprows=1)


import pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(list(df_1))
pd.set_option('display.max_rows', 1000)

2012
df_1["Total!!Estimate!!Bachelor's degree"]
2018
s1=df_1["Estimate!!Percent!!Population 25 years and over!!Bachelor's degree or higher"]

s1=df_1["COLUMN_NAME"]
s2=s1.replace('-',0)
s3=s2.astype(float)
s3.mean()

import matplotlib.pyplot as plt
s3.hist(bins=4)
plt.show()
s3.median()
s3.mean()