Business Analytics - Python Flashcards (Numpy and Pandas)

import numpy as np

import numpy as np

Import convention for Numpy

np.zeroes(())

Create an array of zeroes

np.ones

Create an array of ones

np.arrange(10,25,5)

Create an array of evenly spaced values (step value_

np.linspace(0,2,9)

Create an array of evenly spaced values

np.full((2,2),7)

Create a constant array

np.eye(2)

Create a 2×2 identity matrix

np.random.random((2,2))

Create an array with random values

np.empty((3,2))

Create an empty array

np.int64

Signed 64-bit integer types

np.float32

Standard double-precision floating point

np.complex

Complex numbers represented by 128 floats

np.bool

Boolean type storing TRUE and FALSE values

np.object

Python object type

np.string_

Fixed-length string type

np.unicode_

Fixed-length unicode type

a.shape

Array dimensions

len(a)

Length of array

b.ndim

Number of array dimensions

e.size

Number of array elements

b.dtype

Data type of array elements

b.dtype.name

Name of data type

b.astype(int)

Convert an array to a different type

np.subtract(a,b)

Subtraction

np.add(b,a)

Addition

np.divide(a,b)

Division

np.multiply(a,b)

Multiplication

np.exp(b)

Exponentiation

np.sqrt(b)

Square root

np.sin(a)

Print sines of an array

np.cos(b)

Element-wise cosine

np.log(a)

Element-wise natural logarithm

e.dot(f)

Dot product

a == b

Element-wise comparison

np.array_equal(a, b)

Array-wise comparison

a.sum()

Array-wise sum

a.min()

Array-wise minimum value

b.max(axis=0)

Maximum value of an array row

b.cumsum(axis=1)

Cumulative sum of the elements

a.mean()

Mean

b.median()

Median

a.corrcoef()

Correlation coefficient

np.std(b)

Standard deviation

h = a.view()

Create a view of the array with the same data

np.copy(a)

Create a copy of the array

h = a.copy()

Create a deep copy of the array

a.sort()

Sort an array

c.sort(axis=0)

Sort the elements of an array's axis

a[2]

Select the element at the 2nd index

b[1,2]

Select the element at row 1 column 2

a[0:2]

Select items at index 0 and 1

b[0:2,1]

Select items at rows 0 and 1 in column 1

b[:1]

Select all items at row 0

a[ : :-1]

Reversed array a

a[a<2]

Select elements from a less than 2

b[[1, 0, 1, 0],[0, 1, 2, 0]]

Select elements (1,0),(0,1),(1,2) and (0,0)

b[[1, 0, 1, 0]][:,[0,1,2,0]]

Select a subset of the matrix’s rows and columns

i = np.transpose(b) or i.T

Permute array dimensions

b.ravel()

Flatten the array

g.reshape(3,-2)

Reshape, but don’t change data

h.resize((2,6))

Return a new array with shape (2,6)

np.append(h,g)

Append items to an array

np.insert(a, 1, 5)

Insert items in an array

np.delete(a,[1])

Delete items from an array

np.concatenate((a,d),axis=0)

Concatenate arrays

np.vstack((a,b))

Stack arrays vertically (row-wise)

np.r_[e,f]

Stack arrays vertically (row-wise)

np.hstack((e,f))

Stack arrays horizontally (column-wise)

np.column_stack((a,d)) or np.c_[a,d]

Create stacked column-wise arrays

np.hsplit(a,3)

Split the array horizontally at the 3rd index

np.vsplit(c,2)

Split the array vertically at the 2nd index

df = pd.DataFrame(

{"a" : [4 ,5, 6],

"b" : [7, 8, 9],

"c" : [10, 11, 12]},

index = [1, 2, 3])

Specify values for each column

df = pd.DataFrame(

[[4, 7, 10],

[5, 8, 11],

[6, 9, 12]],

index=[1, 2, 3],

columns=['a', 'b', 'c'])

Specify values for each row

df = pd.DataFrame(

{"a" : [4 ,5, 6],

"b" : [7, 8, 9],

"c" : [10, 11, 12]},

index = pd.MultiIndex.from_tuples(

[('d',1),('d',2),('e',2)],

names=['n','v'])))

Create DataFrame with a MultiIndex

pd.melt(df)

Gather columns into rows

pd.concat([df1,df2])

Append rows of DataFrames

df.pivot(columns='var', values='val')

Spread rows into columns

pd.concat([df1,df2], axis=1)

Append columns of DataFrames

df[df.Length > 7]

Extract rows that meet logical criteria.

df.drop_duplicates()

Remove duplicate rows (only considers columns)

df.head(n)

Select first n rows.

df.tail(n)

Select last n rows.

df.sample(frac=0.5)

Randomly select fraction of rows.

df.sample(n=10)

Randomly select n rows.

df.iloc[10:20]

Select rows by position

df.nlargest(n, 'value')

Select and order top n entries.

df.nsmallest(n, 'value')

Select and order bottom n entries.

df[['width','length','species']]

Select multiple columns with specific names.

df['width'] or df.width

Select single column with specific name.

df.filter(regex='regex')

Select columns whose name matches regular expression regex

df.loc[:,'x2':'x4']

Select all columns between x2 and x4 (inclusive).

df.iloc[:,[1,2,5]]

Select columns in positions 1, 2 and 5 (first column is 0).

df.loc[df['a'] > 10, ['a','c']]

Select rows meeting logical condition, and only the specific columns .

df['w'].value_counts()

Count number of rows with each unique value of variable

len(df)

# of rows in DataFrame

df['w'].nunique()

df.describe()

sum()

Sum values of each object.