pandas Part 10 – Operations on Data

import numpy as np
import pandas as pd

# Let's create a Series object and a DataFrame object to work on.
numSeries = pd.Series([3, 6, 5, 10],
                     index = ['A', 'B', 'C', 'D'])

numDataFrame = pd.DataFrame(np.random.randint(1, 10, (3, 4)),
                           columns = ['A', 'B', 'C', 'D'])

# Let's print out the Series...
numSeries

# and the DataFrame.
numDataFrame

# Now let's apply the unary sin function to the Series.
np.sin(numSeries * np.pi)

# And let's do the same to the DataFrame.
np.sin(numDataFrame * np.pi)

# First let's create two Series objects.
ser1 = pd.Series([5, 3, 1, 6],
                index = ['A', 'B', 'C', 'D'])
ser2 = pd.Series([6, 8, 2, 6],
                index = ['A', 'B', 'C', 'D'])

# Here's ser1.
ser1

# And here's ser2.
ser2

# An example of a binary operation is multiplication. Let's check it out.
ser1 * ser2

# Let's create two other Series objects so that the indices are slightly different.
ser3 = pd.Series([5, 3, 1, 6],
                index = ['A', 'B', 'C', 'D'])
ser4 = pd.Series([6, 8, 2, 6],
                index = ['B', 'D', 'F', 'G'])

# Now let's perfom another common binary operation, addition.
ser3 + ser4

# Again, let's start by creating two DataFrame objects with overlapping indices and column names.
df1 = pd.DataFrame(np.random.randint(1, 10, (3, 4)),
                  columns = ['A', 'B', 'C', 'D'])
df2 = pd.DataFrame(np.random.randint(2, 20, (3, 4)),
                  columns = ['A', 'B', 'C', 'D'])

# Here's df1
df1

# And here's df2
df2

# The time let's use the true division binary operation.
df1 / df2

# Let's define two such DataFrames.
df3 = pd.DataFrame(np.random.randint(1, 10, (3, 4)),
                  columns = ['A', 'B', 'C', 'D'])
df4 = pd.DataFrame(np.random.randint(2, 20, (4, 3)),
                  columns = ['A', 'B', 'E'])

# Here's df3.
df3

# And here's df4.
df4

# And now let's perform the subtraction binary operation on them.
df3 - df4

# Let's create a Series object and a DataFrame object to work on.
ser5 = pd.Series([2, 4, 7, 8],
                index = ['A', 'B', 'C', 'D'])
df5 = pd.DataFrame(np.random.randint(1, 10, (3, 4)),
                  columns = ['A', 'B', 'C', 'D'])

# Here's the Series.
ser5

# And here's the DataFrame.
df5

# Let's see how the subtraction operation works.
ser5 - df5

# Naturally, with subtraction the order matters.
df5 - ser5

# Let's define another Series and another DataFrame.
ser6 = pd.Series([2, 4, 7, 8],
                index = ['A', 'B', 'C', 'D'])
df6 = pd.DataFrame(np.random.randint(1, 10, (3, 4)),
                  columns = ['A', 'C', 'D', 'E'])

# Here's ser6.
ser6

# And here's df6.
df6

# Let's subtract the DataFrame from the Series now:
ser6 - df6

# And the other way around:
df6 - ser6