💡 NumPy Tip: Efficient Filtering with Boolean Masks

Avoid slow Python loops for filtering data. Instead, create a "mask" array of True/False values based on a condition. Applying this mask to your original array instantly selects only the elements where the mask is True, which is significantly faster.

import numpy as np

# Create an array of data
data = np.array([10, 55, 8, 92, 43, 77, 15])

# Create a boolean mask for values greater than 50
high_values_mask = data > 50

# Use the mask to select elements
filtered_data = data[high_values_mask]

print(filtered_data)
# Output: [55 92 77]

Code explanation: A NumPy array data is created. Then, a boolean array high_values_mask is generated, which is True for every element in data greater than 50. This mask is used as an index to efficiently extract and print only those matching elements from the original array.

#Python #NumPy #DataScience #CodingTips #Programming

━━━━━━━━━━━━━━━
By: @CodeProgrammer ✨

import pandas as pd
df1 = pd.DataFrame({'val1': [1, 2]}, index=['A', 'B'])
df2 = pd.DataFrame({'val2': [3, 4]}, index=['A', 'B'])
joined = df1.join(df2)
print(joined)

val1  val2
A     1     3
B     2     4

#59. pd.get_dummies()
Converts categorical variable into dummy/indicator variables (one-hot encoding).

import pandas as pd
s = pd.Series(list('abca'))
dummies = pd.get_dummies(s)
print(dummies)

a  b  c
0  1  0  0
1  0  1  0
2  0  0  1
3  1  0  0

#60. df.nlargest()
Returns the first n rows ordered by columns in descending order.

import pandas as pd
df = pd.DataFrame({'population': [100, 500, 200, 800]})
print(df.nlargest(2, 'population'))

population
3         800
1         500

---
#DataAnalysis #NumPy #Arrays

Part 6: NumPy - Array Creation & Manipulation

#61. np.array()
Creates a NumPy ndarray.

import numpy as np
arr = np.array([1, 2, 3])
print(arr)

[1 2 3]

#62. np.arange()
Returns an array with evenly spaced values within a given interval.

import numpy as np
arr = np.arange(0, 5)
print(arr)

[0 1 2 3 4]

#63. np.linspace()
Returns an array with evenly spaced numbers over a specified interval.

import numpy as np
arr = np.linspace(0, 10, 5)
print(arr)

[ 0.   2.5  5.   7.5 10. ]

#64. np.zeros()
Returns a new array of a given shape and type, filled with zeros.

import numpy as np
arr = np.zeros((2, 3))
print(arr)

[[0. 0. 0.]
 [0. 0. 0.]]

#65. np.ones()
Returns a new array of a given shape and type, filled with ones.

import numpy as np
arr = np.ones((2, 3))
print(arr)

[[1. 1. 1.]
 [1. 1. 1.]]

#66. np.random.rand()
Creates an array of the given shape and populates it with random samples from a uniform distribution over [0, 1).

import numpy as np
arr = np.random.rand(2, 2)
print(arr)

[[0.13949386 0.2921446 ]
 [0.52273283 0.77122228]]
(Note: Output values will be random)

#67. arr.reshape()
Gives a new shape to an array without changing its data.

import numpy as np
arr = np.arange(6)
reshaped_arr = arr.reshape((2, 3))
print(reshaped_arr)

[[0 1 2]
 [3 4 5]]

#68. np.concatenate()
Joins a sequence of arrays along an existing axis.

import numpy as np
a = np.array([[1, 2]])
b = np.array([[3, 4]])
print(np.concatenate((a, b), axis=0))

[[1 2]
 [3 4]]

#69. np.vstack()
Stacks arrays in sequence vertically (row wise).

import numpy as np
a = np.array([1, 2])
b = np.array([3, 4])
print(np.vstack((a, b)))

[[1 2]
 [3 4]]

#70. np.hstack()
Stacks arrays in sequence horizontally (column wise).

import numpy as np
a = np.array([1, 2])
b = np.array([3, 4])
print(np.hstack((a, b)))

[1 2 3 4]

---
#DataAnalysis #NumPy #Math #Statistics

Part 7: NumPy - Mathematical & Statistical Functions

#71. np.mean()
Computes the arithmetic mean along the specified axis.

import numpy as np
arr = np.array([1, 2, 3, 4, 5])
print(np.mean(arr))

3.0

#72. np.median()
Computes the median along the specified axis.

import numpy as np
arr = np.array([1, 2, 3, 4, 5])
print(np.median(arr))

3.0

#73. np.std()
Computes the standard deviation along the specified axis.