In Python, NumPy is the cornerstone of scientific computing, offering high-performance multidimensional arrays and tools for working with them—critical for data science interviews and real-world applications! 📊

import numpy as np

# Array Creation - The foundation of NumPy
arr = np.array([1, 2, 3])
zeros = np.zeros((2, 3))        # 2x3 matrix of zeros
ones = np.ones((2, 2), dtype=int)  # Integer matrix
arange = np.arange(0, 10, 2)    # [0 2 4 6 8]
linspace = np.linspace(0, 1, 5) # [0.  0.25 0.5  0.75 1.  ]
print(linspace)

# Array Attributes - Master your data's structure
matrix = np.array([[1, 2, 3], [4, 5, 6]])
print(matrix.shape)  # Output: (2, 3)
print(matrix.ndim)   # Output: 2
print(matrix.dtype)  # Output: int64
print(matrix.size)   # Output: 6

# Indexing & Slicing - Precision data access
data = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
print(data[1, 2])      # Output: 6 (row 1, col 2)
print(data[0:2, 1:3])  # Output: [[2 3], [5 6]]
print(data[:, -1])     # Output: [3 6 9] (last column)

# Reshaping Arrays - Transform dimensions effortlessly
flat = np.arange(6)
reshaped = flat.reshape(2, 3)
raveled = reshaped.ravel()
print(reshaped)
# Output: [[0 1 2], [3 4 5]]
print(raveled)  # Output: [0 1 2 3 4 5]

# Stacking Arrays - Combine datasets vertically/horizontally
a = np.array([1, 2, 3])
b = np.array([4, 5, 6])
print(np.vstack((a, b)))  # Vertical stack
# Output: [[1 2 3], [4 5 6]]
print(np.hstack((a, b)))  # Horizontal stack
# Output: [1 2 3 4 5 6]

# Mathematical Operations - Vectorized calculations
x = np.array([1, 2, 3])
y = np.array([4, 5, 6])
print(x + y)       # Output: [5 7 9]
print(x * 2)       # Output: [2 4 6]
print(np.dot(x, y)) # Output: 32 (1*4 + 2*5 + 3*6)

# Broadcasting Magic - Operate on mismatched shapes
matrix = np.array([[1, 2, 3], [4, 5, 6]])
scalar = 10
print(matrix + scalar)
# Output: [[11 12 13], [14 15 16]]

# Aggregation Functions - Statistical power in one line
values = np.array([1, 5, 3, 9, 7])
print(np.sum(values))   # Output: 25
print(np.mean(values))  # Output: 5.0
print(np.max(values))   # Output: 9
print(np.std(values))   # Output: 2.8284271247461903

# Boolean Masking - Filter data like a pro
temperatures = np.array([18, 25, 12, 30, 22])
hot_days = temperatures > 24
print(temperatures[hot_days])  # Output: [25 30]

# Random Number Generation - Simulate real-world data
print(np.random.rand(2, 2))      # Uniform distribution
print(np.random.randn(3))        # Normal distribution
print(np.random.randint(0, 10, (2, 3)))  # Random integers

# Linear Algebra Essentials - Solve equations like a physicist
A = np.array([[3, 1], [1, 2]])
b = np.array([9, 8])
x = np.linalg.solve(A, b)
print(x)  # Output: [2. 3.] (Solution to 3x+y=9 and x+2y=8)

# Matrix inverse and determinant
print(np.linalg.inv(A))   # Output: [[ 0.4 -0.2], [-0.2  0.6]]
print(np.linalg.det(A))   # Output: 5.0

# File Operations - Save/load your computational work
data = np.array([[1, 2], [3, 4]])
np.save('array.npy', data)
loaded = np.load('array.npy')
print(np.array_equal(data, loaded))  # Output: True

# Interview Power Move: Vectorization vs Loops
# 10x faster than native Python loops!
def square_sum(n):
    arr = np.arange(n)
    return np.sum(arr ** 2)

print(square_sum(5))  # Output: 30 (0²+1²+2²+3²+4²)

# Pro Tip: Memory-efficient data processing
# Process 1GB array without loading entire dataset
large_array = np.memmap('large_data.bin', dtype='float32', mode='r', shape=(1000000, 100))
print(large_array[0:5, 0:3])  # Process small slice

By: @DataScienceQ 🚀

#Python #NumPy #DataScience #CodingInterview #MachineLearning #ScientificComputing #DataAnalysis #Programming #TechJobs #DeveloperTips

💡 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.