Load, Select

Import

import pandas as pd

Create dataframe

dataFrameName = pd.DataFrame({
  'Product ID': [1, 2, 3, 4],
  'Product Name': ['t-shirt', 't-shirt', 'skirt', 'skirt'],
  'Color': ['blue', 'green', 'red', 'black']
})

# or 

dataFrameName = pd.DataFrame(
  [[1, 'San Diego', 100],
  [2, 'Los Angeles', 120],
  [3, 'San Francisco', 90],
  [4, 'Sacramento', 115]],
  columns=['Store ID', 'Location', 'Number of Employees']
)

Print dataframe

print(dataFrameName)

# shows first few rows
print(dataFrameName.head())

# shows some stats about each column
print(dataFrameName)

Select column

# use this one, less likerly to error, due to syntax
dataFrameName['colName']

# or 

dataFrameName.colName

# select multiple
dataFrameName[['colName', 'colName1']]

# select with logic
dataFrameName[dataFrameName['colName'] == 78]

Select row

dataFrameName.iloc[0]

dataFrameName.iloc[1:8]

dataFrameName.iloc[-1]

# yes i thought it not being called iloc was odd
dataFrameName.loc[[1, 3, 5]]

# select with logic
dataFrameName[(dataFrameName.age > 30) | (dataFrameName.name == 'benji')]

# or
# returns rows if they have val
dataFrameName[dataFrameName['colName'].isin(['val','val','val'])]

Reseting Index

Note: the indexs are carried over from the previous data frame, we can reset them

# resets them back to 0...n, note a new column is made with the old indies
new_dataFrameName = dataFrameName.reset_index()

# this removes that new column
new_dataFrameName = dataFrameName.reset_index(drop = True)

# modifys current data frame
dataFrameName.reset_index(drop = True, implace = True)