import pandas as pd
df = pd.DataFrame({'A': [1, 2, 1], 'B': ['a', 'b', 'a']})
print(df.drop_duplicates())

A  B
0  1  a
1  2  b

#37. df.sort_values()
Sorts by the values along either axis.

import pandas as pd
df = pd.DataFrame({'Age': [25, 22, 30]})
print(df.sort_values(by='Age'))

Age
1   22
0   25
2   30

#38. df.sort_index()
Sorts object by labels (along an axis).

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3]}, index=[10, 5, 8])
print(df.sort_index())

A
5  2
8  3
10 1

#39. pd.cut()
Bins values into discrete intervals.

import pandas as pd
ages = pd.Series([22, 35, 58, 8, 42])
age_bins = pd.cut(ages, bins=[0, 18, 35, 60], labels=['Child', 'Adult', 'Senior'])
print(age_bins)

0     Adult
1     Adult
2    Senior
3     Child
4    Senior
dtype: category
Categories (3, object): ['Child' < 'Adult' < 'Senior']

#40. pd.qcut()
Quantile-based discretization function (bins into equal-sized groups).

import pandas as pd
data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
quartiles = pd.qcut(data, 4, labels=False)
print(quartiles)

0    0
1    0
2    0
3    1
4    1
5    2
6    2
7    3
8    3
9    3
dtype: int64

#41. s.str.contains()
Tests if a pattern or regex is contained within a string of a Series.

import pandas as pd
s = pd.Series(['apple', 'banana', 'apricot'])
print(s[s.str.contains('ap')])

0      apple
2    apricot
dtype: object

#42. s.str.split()
Splits strings around a given separator/delimiter.

import pandas as pd
s = pd.Series(['a_b', 'c_d'])
print(s.str.split('_', expand=True))

0  1
0  a  b
1  c  d

#43. s.str.lower()
Converts strings in the Series to lowercase.

import pandas as pd
s = pd.Series(['HELLO', 'World'])
print(s.str.lower())

0    hello
1    world
dtype: object

#44. s.str.strip()
Removes leading and trailing whitespace.

import pandas as pd
s = pd.Series(['  hello  ', ' world '])
print(s.str.strip())

0    hello
1    world
dtype: object

#45. s.dt.year
Extracts the year from a datetime Series.

import pandas as pd
s = pd.to_datetime(pd.Series(['2023-01-01', '2024-05-10']))
print(s.dt.year)

0    2023
1    2024
dtype: int64

---
#DataAnalysis #Pandas #Grouping #Aggregation

Part 4: Pandas - Grouping & Aggregation

#46. df.groupby()
Groups a DataFrame using a mapper or by a Series of columns.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
grouped = df.groupby('Team')
print(grouped)

<pandas.core.groupby.generic.DataFrameGroupBy object at 0x...>

#47. groupby.agg()
Aggregates using one or more operations over the specified axis.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
agg_df = df.groupby('Team').agg(['mean', 'sum'])
print(agg_df)

Points     
        mean  sum
Team             
A         11   22
B          7   14

#48. groupby.size()
Computes group sizes.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B', 'A']})
print(df.groupby('Team').size())

Team
A    3
B    2
dtype: int64

#49. groupby.count()
Computes the count of non-NA cells for each group.

import pandas as pd
import numpy as np
df = pd.DataFrame({'Team': ['A', 'B', 'A'], 'Score': [1, np.nan, 3]})
print(df.groupby('Team').count())

Score
Team       
A         2
B         0

#50. groupby.mean()
Computes the mean of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').mean())

Points
Team        
A         11
B          7

#51. groupby.sum()
Computes the sum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').sum())

Points
Team        
A         22
B         14

#52. groupby.min()
Computes the minimum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').min())

Points
Team        
A         10
B          6

#53. groupby.max()
Computes the maximum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').max())

Points
Team        
A         12
B          8

#54. df.pivot_table()
Creates a spreadsheet-style pivot table as a DataFrame.

import pandas as pd
df = pd.DataFrame({'A': ['foo', 'foo', 'bar'], 'B': ['one', 'two', 'one'], 'C': [1, 2, 3]})
pivot = df.pivot_table(values='C', index='A', columns='B')
print(pivot)

B    one  two
A            
bar  3.0  NaN
foo  1.0  2.0

#55. pd.crosstab()
Computes a cross-tabulation of two (or more) factors.

import pandas as pd
df = pd.DataFrame({'A': ['foo', 'foo', 'bar'], 'B': ['one', 'two', 'one']})
crosstab = pd.crosstab(df.A, df.B)
print(crosstab)

B    one  two
A            
bar    1    0
foo    1    1

---
#DataAnalysis #Pandas #Merging #Joining

Part 5: Pandas - Merging & Concatenating

#56. pd.merge()
Merges DataFrame or named Series objects with a database-style join.

import pandas as pd
df1 = pd.DataFrame({'key': ['A', 'B'], 'val1': [1, 2]})
df2 = pd.DataFrame({'key': ['A', 'B'], 'val2': [3, 4]})
merged = pd.merge(df1, df2, on='key')
print(merged)

key  val1  val2
0   A     1     3
1   B     2     4

#57. pd.concat()
Concatenates pandas objects along a particular axis.

import pandas as pd
df1 = pd.DataFrame({'A': [1, 2]})
df2 = pd.DataFrame({'A': [3, 4]})
concatenated = pd.concat([df1, df2])
print(concatenated)

A
0  1
1  2
0  3
1  4

#58. df.join()
Joins columns with other DataFrame(s) on index or on a key column.