Pandas Exercises And Solutions

import numpy as np
import pandas as pd

np.random.seed(42)

# From list
l = [1, 2, 3, 4, 5, 6]
serie = pd.Series(l)
print(serie)

# From NumPy array
array = np.array([1, 2, 3, 4, 5, 6])
serie = pd.Series(array)
print(serie)

# From dictionary
d = {"A": 1, "B": 2, "C": 3}
serie = pd.Series(d)
print(serie)

# From NumPy array
array = np.random.randint(1, 10, size = (5, 5))
dataframe = pd.DataFrame(array)
dataframe

# From dictionary
d = {
    "A": np.random.randint(10, 100, size = 5),
    "B": np.linspace(1, 10, 5),
    "C": np.random.randn(5)
}
dataframe = pd.DataFrame(d)
dataframe

# From list of tuples
t = [(1, 2, 3), (4, 5, 6), (7, 8, 9)]
dataframe = pd.DataFrame(t)
dataframe

s1 = pd.Series([1, 2, 3, 4, 5])
s2 = pd.Series([4, 5, 6, 7, 8])

# Method 1
dataframe = pd.DataFrame({"ser1": s1, "ser2": s2})
dataframe = pd.DataFrame({"ser1": s1, "ser2": s2}, index = s1.index)
dataframe

# Method 2
dataframe = pd.concat([s1, s2], axis = 1)
dataframe

# Method 3
s1.name = "ser1"
s2.name = "ser2"

dataframe = s1.to_frame().join(s2)
dataframe

s1 = pd.Series([1, 2, 3, 4, 5])
s2 = pd.Series([4, 5, 6, 7, 8])

# Method 1: Using Pandas function
filtering_results = s1.isin(s2)
indices = s1[filtering_results].index

indices

# Method 2: Using NumPy function
indices = np.where(s1.isin(s2))
indices

# Method 3: Using Python
indices = []

for value in s1.values:
    if value in s2.values:
        indices.append(s1[s1 == value].index[0])
indices

s1 = pd.Series([1, 2, 3, 4, 5])
s2 = pd.Series([4, 5, 6, 7, 8])

# Method 1
unique_s1 = s1[~s1.isin(s2)]
unique_s2 = s2[~s2.isin(s1)]

unique_elements = np.concatenate([unique_s1, unique_s2])
unique_elements

# Method 2
concat = pd.concat([s1, s2])
unique_elements = concat[~concat.duplicated(keep = False)].values
unique_elements

df = pd.DataFrame(np.random.rand(10, 5) * 10, columns = [f"Col {i}" for i in range(5)])
df

df.sort_values("Col 0")

df.sort_values(by = ["Col 2", "Col 4"])

df.columns = [f"{i}_column" for i in range(5)]
df

df.index = [f"{i}_row" for i in range(10)]
df