Tutorial on Python Library: pandas

---

Bikash Santra

Indian Statistical Institute, Kolkata

---

1. Import library

import pandas as pd

2. Intro

df = pd.DataFrame(
    {
        "Name": [
            "Braund, Mr. Owen Harris",
            "Allen, Mr. William Henry",
            "Bonnell, Miss. Elizabeth",
        ],
        "Age": [22, 35, 58],
        "Sex": ["male", "male", "female"],
    }
)

print(df)

                       Name  Age     Sex
0   Braund, Mr. Owen Harris   22    male
1  Allen, Mr. William Henry   35    male
2  Bonnell, Miss. Elizabeth   58  female

df

	Name	Age	Sex
0	Braund, Mr. Owen Harris	22	male
1	Allen, Mr. William Henry	35	male
2	Bonnell, Miss. Elizabeth	58	female

xx = df["Age"]

xx

0    22
1    35
2    58
Name: Age, dtype: int64

df["Age"].max()

58

xx.min()

22

xx.mean()

38.333333333333336

xx.std()

18.230011885167087

df

	Name	Age	Sex
0	Braund, Mr. Owen Harris	22	male
1	Allen, Mr. William Henry	35	male
2	Bonnell, Miss. Elizabeth	58	female

## Describing numerical data

df.describe()

	Age
count	3.000000
mean	38.333333
std	18.230012
min	22.000000
25%	28.500000
50%	35.000000
75%	46.500000
max	58.000000

3. From Dictionary to Dataframe

dict_1 = {"Country": ["Brazil", "Russia", "India", "China", "South Africa"],
       "Capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
       "Area": [8.516, 17.10, 3.286, 9.597, 1.221],
       "Population": [200.4, 143.5, 1252, 1357, 52.98] }

print(dict_1)

{'Country': ['Brazil', 'Russia', 'India', 'China', 'South Africa'], 'Capital': ['Brasilia', 'Moscow', 'New Dehli', 'Beijing', 'Pretoria'], 'Area': [8.516, 17.1, 3.286, 9.597, 1.221], 'Population': [200.4, 143.5, 1252, 1357, 52.98]}

brics = pd.DataFrame(dict_1)

brics

	Country	Capital	Area	Population
0	Brazil	Brasilia	8.516	200.40
1	Russia	Moscow	17.100	143.50
2	India	New Dehli	3.286	1252.00
3	China	Beijing	9.597	1357.00
4	South Africa	Pretoria	1.221	52.98

brics.head(3)

	Country	Capital	Area	Population
0	Brazil	Brasilia	8.516	200.4
1	Russia	Moscow	17.100	143.5
2	India	New Dehli	3.286	1252.0

print(brics)

        Country    Capital    Area  Population
0        Brazil   Brasilia   8.516      200.40
1        Russia     Moscow  17.100      143.50
2         India  New Dehli   3.286     1252.00
3         China    Beijing   9.597     1357.00
4  South Africa   Pretoria   1.221       52.98

# Set the index for brics
brics.index = ["BR", "RU", "IN", "CH", "SA"]

# Print out brics with new index values
print(brics)

         Country    Capital    Area  Population
BR        Brazil   Brasilia   8.516      200.40
RU        Russia     Moscow  17.100      143.50
IN         India  New Dehli   3.286     1252.00
CH         China    Beijing   9.597     1357.00
SA  South Africa   Pretoria   1.221       52.98

## Describing numerical data 

brics.describe()

	Area	Population
count	5.000000	5.000000
mean	7.944000	601.176000
std	6.200557	645.261454
min	1.221000	52.980000
25%	3.286000	143.500000
50%	8.516000	200.400000
75%	9.597000	1252.000000
max	17.100000	1357.000000

brics.info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, BR to SA
Data columns (total 4 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   Country     5 non-null      object 
 1   Capital     5 non-null      object 
 2   Area        5 non-null      float64
 3   Population  5 non-null      float64
dtypes: float64(2), object(2)
memory usage: 200.0+ bytes

import numpy as np
dict_2 = {"Name": ["Alice", "Juliet", "Alex", "Sara", "Oliver"],
         "Statistical Inference": [87,np.nan,96,65,87],
         "Statistical Methods": [94,87,58,63,72],
         "Vectors & Matrices":[92,74,57,96,88],
         "Remarks":['Excellent','Good','Good','Good','Very Good']}
print(dict_2) 

{'Name': ['Alice', 'Juliet', 'Alex', 'Sara', 'Oliver'], 'Statistical Inference': [87, nan, 96, 65, 87], 'Statistical Methods': [94, 87, 58, 63, 72], 'Vectors & Matrices': [92, 74, 57, 96, 88], 'Remarks': ['Excellent', 'Good', 'Good', 'Good', 'Very Good']}

brics1 = pd.DataFrame(dict_2)
print(brics1)

     Name  Statistical Inference  Statistical Methods  Vectors & Matrices  \
0   Alice                   87.0                   94                  92   
1  Juliet                    NaN                   87                  74   
2    Alex                   96.0                   58                  57   
3    Sara                   65.0                   63                  96   
4  Oliver                   87.0                   72                  88   

     Remarks  
0  Excellent  
1       Good  
2       Good  
3       Good  
4  Very Good  

brics1

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

brics1.describe()

	Statistical Inference	Statistical Methods	Vectors & Matrices
count	4.000000	5.000000	5.000000
mean	83.750000	74.800000	81.400000
std	13.200379	15.385058	15.962456
min	65.000000	58.000000	57.000000
25%	81.500000	63.000000	74.000000
50%	87.000000	72.000000	88.000000
75%	89.250000	87.000000	92.000000
max	96.000000	94.000000	96.000000

brics1.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5 entries, 0 to 4
Data columns (total 5 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   Name                   5 non-null      object 
 1   Statistical Inference  4 non-null      float64
 2   Statistical Methods    5 non-null      int64  
 3   Vectors & Matrices     5 non-null      int64  
 4   Remarks                5 non-null      object 
dtypes: float64(1), int64(2), object(2)
memory usage: 328.0+ bytes

brics1["Vectors & Matrices"]

0    92
1    74
2    57
3    96
4    88
Name: Vectors & Matrices, dtype: int64

brics1.index = ["P1", "P2", "P3", "P4", "P5"]
print(brics1)

      Name  Statistical Inference  Statistical Methods  Vectors & Matrices  \
P1   Alice                   87.0                   94                  92   
P2  Juliet                    NaN                   87                  74   
P3    Alex                   96.0                   58                  57   
P4    Sara                   65.0                   63                  96   
P5  Oliver                   87.0                   72                  88   

      Remarks  
P1  Excellent  
P2       Good  
P3       Good  
P4       Good  
P5  Very Good  

brics1

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
P1	Alice	87.0	94	92	Excellent
P2	Juliet	NaN	87	74	Good
P3	Alex	96.0	58	57	Good
P4	Sara	65.0	63	96	Good
P5	Oliver	87.0	72	88	Very Good

brics1.shape

(5, 5)

4. Write and Read to/from csv or excel files

## Write to EXCEL

brics1.to_excel("brics_test.xlsx", sheet_name="brics_1", index=True)

## Write to CSV

brics1.to_csv("brics_test.csv", header=True, index=False)

## Read from EXCEL

titanic = pd.read_excel("brics_test.xlsx", sheet_name="brics_1", index_col=0)
print(titanic)

      Name  Statistical Inference  Statistical Methods  Vectors & Matrices  \
P1   Alice                   87.0                   94                  92   
P2  Juliet                    NaN                   87                  74   
P3    Alex                   96.0                   58                  57   
P4    Sara                   65.0                   63                  96   
P5  Oliver                   87.0                   72                  88   

      Remarks  
P1  Excellent  
P2       Good  
P3       Good  
P4       Good  
P5  Very Good  

titanic

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
P1	Alice	87.0	94	92	Excellent
P2	Juliet	NaN	87	74	Good
P3	Alex	96.0	58	57	Good
P4	Sara	65.0	63	96	Good
P5	Oliver	87.0	72	88	Very Good

titanic.head(3)

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
P1	Alice	87.0	94	92	Excellent
P2	Juliet	NaN	87	74	Good
P3	Alex	96.0	58	57	Good

## Read from EXCEL

titanic_csv = pd.read_csv("brics_test.csv")#, index_col=0) ## include index_col only when index is present in the csv file
print(titanic_csv)

     Name  Statistical Inference  Statistical Methods  Vectors & Matrices  \
0   Alice                   87.0                   94                  92   
1  Juliet                    NaN                   87                  74   
2    Alex                   96.0                   58                  57   
3    Sara                   65.0                   63                  96   
4  Oliver                   87.0                   72                  88   

     Remarks  
0  Excellent  
1       Good  
2       Good  
3       Good  
4  Very Good  

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

titanic_csv.head(2)

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good

capitals = titanic_csv["Remarks"]

capitals.head()

0    Excellent
1         Good
2         Good
3         Good
4    Very Good
Name: Remarks, dtype: object

type(titanic_csv["Remarks"])

pandas.core.series.Series

type(capitals)

pandas.core.series.Series

capitals.shape

(5,)

5. Subset selection and applying formulas to new columns

cap_area = titanic_csv[["Name", "Remarks"]]
cap_area

	Name	Remarks
0	Alice	Excellent
1	Juliet	Good
2	Alex	Good
3	Sara	Good
4	Oliver	Very Good

cap_area.shape

(5, 2)

## Remove index_col=0 and excute the earlier cells, see the change

### Data fetching based on conditions

titanic_subset = titanic_csv[titanic_csv["Statistical Methods"] > 70.0]

titanic_subset

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
4	Oliver	87.0	72	88	Very Good

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

class_23 = titanic_csv[titanic_csv["Remarks"].isin(["Excellent", "Very Good"])]
class_23

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
4	Oliver	87.0	72	88	Very Good

## AND (&) OR (|) 

cond = titanic_csv[(titanic_csv["Remarks"] == "Good") | (titanic_csv["Vectors & Matrices"] >= 90.00)]
cond

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good

titanic_csv[(titanic_csv["Remarks"] == "Good") | (titanic_csv["Vectors & Matrices"] >= 90.00)]

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good

cond = titanic_csv[(titanic_csv["Remarks"] == "Good") & (titanic_csv["Vectors & Matrices"] >= 70.00)]
cond

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
1	Juliet	NaN	87	74	Good
3	Sara	65.0	63	96	Good

## Display only NOT NULL values

area_no_na = titanic_csv[titanic_csv["Statistical Inference"].notna()]
area_no_na

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

6. Index Location

test = titanic_csv.iloc[2:3, 1:3]

test

	Statistical Inference	Statistical Methods
2	96.0	58

ti = titanic_csv.copy()
ti

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

ti.iloc[2:3, 1:3] = np.nan

ti

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94.0	92	Excellent
1	Juliet	NaN	87.0	74	Good
2	Alex	NaN	NaN	57	Good
3	Sara	65.0	63.0	96	Good
4	Oliver	87.0	72.0	88	Very Good

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks
0	Alice	87.0	94	92	Excellent
1	Juliet	NaN	87	74	Good
2	Alex	96.0	58	57	Good
3	Sara	65.0	63	96	Good
4	Oliver	87.0	72	88	Very Good

s = pd.Series([20, 40, 50, np.nan, 70], index=[0,1,2,3,4])

s

0    20.0
1    40.0
2    50.0
3     NaN
4    70.0
dtype: float64

titanic_csv['Python'] = s.values

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python
0	Alice	87.0	94	92	Excellent	20.0
1	Juliet	NaN	87	74	Good	40.0
2	Alex	96.0	58	57	Good	50.0
3	Sara	65.0	63	96	Good	NaN
4	Oliver	87.0	72	88	Very Good	70.0

titanic_csv['1st'] = titanic_csv["Statistical Inference"] > 50

xx = titanic_csv[["Statistical Inference", "Statistical Methods", "Vectors & Matrices"]]
xx

	Statistical Inference	Statistical Methods	Vectors & Matrices
0	87.0	94	92
1	NaN	87	74
2	96.0	58	57
3	65.0	63	96
4	87.0	72	88

titanic_csv['2nd'] = xx.mean(axis=1)

titanic_csv['3rd'] = xx.max(axis=1)

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python	1st	2nd	3rd
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python	1st	2nd	3rd
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0

titanic_csv["new"] = titanic_csv["Statistical Methods"] * 1.882
titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python	1st	2nd	3rd	new
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504

titanic_csv["new_1"] = titanic_csv["Statistical Methods"] / titanic_csv["Vectors & Matrices"]
titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python	1st	2nd	3rd	new	new_1
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

7. Renaming column headers

titanic_csv = titanic_csv.rename(
    columns={
        "new": "Multiply",
        "new_1": "Ratio",
    }
)

titanic_csv

	Name	Statistical Inference	Statistical Methods	Vectors & Matrices	Remarks	Python	1st	2nd	3rd	Multiply	Ratio
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

titanic_csv = titanic_csv.rename(columns=str.lower)
titanic_csv.head()

	name	statistical inference	statistical methods	vectors & matrices	remarks	python	1st	2nd	3rd	multiply	ratio
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

titanic_csv = titanic_csv.rename(columns=str.capitalize)
titanic_csv.head()

	Name	Statistical inference	Statistical methods	Vectors & matrices	Remarks	Python	1st	2nd	3rd	Multiply	Ratio
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

titanic_csv = titanic_csv.rename(columns=str.upper)
titanic_csv.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

8. Sorting the table

titanic_csv.sort_values(by="STATISTICAL METHODS", ascending=True).head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739

titanic_csv_1 = titanic_csv.sort_values(by="STATISTICAL METHODS", ascending=True).copy()
titanic_csv_1.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739

titanic_csv

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

good = titanic_csv[titanic_csv["REMARKS"] == "Good"].copy()
good

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250

s = pd.Series(["tezpur", "kolkata", "tezpur"], index=[1,2,3])
good["Location"] = s.values

good

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Location
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	tezpur
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	kolkata
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	tezpur

titanic_csv

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

titanic_csv.index = ["BR", "RU", "IN", "CH", "SA"]
titanic_csv.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
BR	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
RU	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
IN	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
CH	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
SA	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

brics

	Country	Capital	Area	Population
BR	Brazil	Brasilia	8.516	200.40
RU	Russia	Moscow	17.100	143.50
IN	India	New Dehli	3.286	1252.00
CH	China	Beijing	9.597	1357.00
SA	South Africa	Pretoria	1.221	52.98

merged = pd.concat([titanic_csv, brics], axis=1)
merged.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Country	Capital	Area	Population
BR	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	Brazil	Brasilia	8.516	200.40
RU	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	Russia	Moscow	17.100	143.50
IN	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	India	New Dehli	3.286	1252.00
CH	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	China	Beijing	9.597	1357.00
SA	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	South Africa	Pretoria	1.221	52.98

titanic_csv.index = [0, 1, 2, 3, 4]
titanic_csv.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1 = titanic_csv[0:3].copy()
x1

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544

x2 = titanic_csv[3:5].copy()
x2

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1_x2 = pd.concat([x1, x2], axis=0)
x1_x2.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

titi = titanic_csv.sort_values("STATISTICAL METHODS")
titi

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739

titanic_csv

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544

x2.head()

	NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1x2 = pd.concat([x1, x2], keys=["X1", "X2"])

x1x2

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

9. Text manipulation

x1x2["NAME"].str.lower()

X1  0     alice
    1    juliet
    2      alex
X2  3      sara
    4    oliver
Name: NAME, dtype: object

x1x2["REMARKS"].str.split(" ")

X1  0     [Excellent]
    1          [Good]
    2          [Good]
X2  3          [Good]
    4    [Very, Good]
Name: REMARKS, dtype: object

x1x2["REMARKS"].str.split(" ").str.get(1)

X1  0     NaN
    1     NaN
    2     NaN
X2  3     NaN
    4    Good
Name: REMARKS, dtype: object

x1x2["REMARKS"].str.contains("Good")

X1  0    False
    1     True
    2     True
X2  3     True
    4     True
Name: REMARKS, dtype: bool

x1x2[x1x2["REMARKS"].str.contains("Good")]

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1x2

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

#Longest name 
x1x2["NAME"].str.len()

X1  0    5
    1    6
    2    4
X2  3    4
    4    6
Name: NAME, dtype: int64

x1x2["NAME"].str.len().idxmax()

('X1', 1)

# iloc: location by index of rows and columns
# loc: location by labels of rows and columns

x1x2.loc[x1x2["NAME"].str.len().idxmax(), "NAME"]

'Juliet'

x1x2["Rem:Short"] = x1x2["REMARKS"].replace({"Good": "G", "Very Good": "V", "Excellent": "E"})

x1x2

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

10. Renaming the column labels

x1x2.columns

Index(['NAME', 'STATISTICAL INFERENCE', 'STATISTICAL METHODS',
       'VECTORS & MATRICES', 'REMARKS', 'PYTHON', '1ST', '2ND', '3RD',
       'MULTIPLY', 'RATIO', 'Rem:Short'],
      dtype='object')

x1x2=x1x2.rename(columns={'Rem:Short':'RM'})
x1x2.columns

Index(['NAME', 'STATISTICAL INFERENCE', 'STATISTICAL METHODS',
       'VECTORS & MATRICES', 'REMARKS', 'PYTHON', '1ST', '2ND', '3RD',
       'MULTIPLY', 'RATIO', 'RM'],
      dtype='object')

x1x2

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	RM
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2 = x1x2.rename(columns={'RM':'Rem:Short'})
x1x2.columns

Index(['NAME', 'STATISTICAL INFERENCE', 'STATISTICAL METHODS',
       'VECTORS & MATRICES', 'REMARKS', 'PYTHON', '1ST', '2ND', '3RD',
       'MULTIPLY', 'RATIO', 'Rem:Short'],
      dtype='object')

x1x2

		NAME	STATISTICAL INFERENCE	STATISTICAL METHODS	VECTORS & MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2.columns = x1x2.columns.str.replace(' ', '_')
x1x2.columns

Index(['NAME', 'STATISTICAL_INFERENCE', 'STATISTICAL_METHODS',
       'VECTORS_&_MATRICES', 'REMARKS', 'PYTHON', '1ST', '2ND', '3RD',
       'MULTIPLY', 'RATIO', 'Rem:Short'],
      dtype='object')

x1x2

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

### Dropping the columns

# Column drop
x1x2.drop('Rem:Short', axis=1, inplace=False).head()
# x1x2.head()

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1x2

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2.drop('Rem:Short', axis=1, inplace=False)
x1x2.head()

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

temp_x = x1x2.copy()
temp_x.drop(['Rem:Short', 'STATISTICAL_METHODS'], axis=1, inplace=True)

temp_x

		NAME	STATISTICAL_INFERENCE	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	0	Alice	87.0	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739
	1	Juliet	NaN	74	Good	40.0	False	80.500000	87.0	163.734	1.175676
	2	Alex	96.0	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

# Row drop
temp_x.drop(temp_x.index[[0, 1]], axis=0, inplace=True)

temp_x

		NAME	STATISTICAL_INFERENCE	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO
X1	2	Alex	96.0	57	Good	50.0	True	70.333333	96.0	109.156	1.017544
X2	3	Sara	65.0	96	Good	NaN	True	74.666667	96.0	118.566	0.656250
	4	Oliver	87.0	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182

x1x2

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

# The loc method is used to select rows and columns by label.
# The iloc method is used to select rows and columns by integer position

x1x2.loc[('X1',0):('X2',3), :] # last inclusive

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G

x1x2.tail(4)

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2_T = x1x2.T
x1x2_T

	X1			X2
	0	1	2	3	4
NAME	Alice	Juliet	Alex	Sara	Oliver
STATISTICAL_INFERENCE	87.0	NaN	96.0	65.0	87.0
STATISTICAL_METHODS	94	87	58	63	72
VECTORS_&_MATRICES	92	74	57	96	88
REMARKS	Excellent	Good	Good	Good	Very Good
PYTHON	20.0	40.0	50.0	NaN	70.0
1ST	True	False	True	True	True
2ND	91.0	80.5	70.333333	74.666667	82.333333
3RD	94.0	87.0	96.0	96.0	88.0
MULTIPLY	176.908	163.734	109.156	118.566	135.504
RATIO	1.021739	1.175676	1.017544	0.65625	0.818182
Rem:Short	E	G	G	G	V

x1x2

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

11. Random sampling

x1x2.sample(n=2)

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	1	Juliet	NaN	87	74	Good	40.0	False	80.5	87.0	163.734	1.175676	G
	0	Alice	87.0	94	92	Excellent	20.0	True	91.0	94.0	176.908	1.021739	E

12. Inserting rows and columns

x1x2

		NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
X1	0	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
	1	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
	2	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
X2	3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
	4	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2.loc[5] = ["Oliver", 87.0, 72, 88, "Very Good", 70.0, True, 82.333333, 88.0, 135.504, 0.818182, "V"]

x1x2

	NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
(X1, 0)	Alice	87.0	94	92	Excellent	20.0	True	91.000000	94.0	176.908	1.021739	E
(X1, 1)	Juliet	NaN	87	74	Good	40.0	False	80.500000	87.0	163.734	1.175676	G
(X1, 2)	Alex	96.0	58	57	Good	50.0	True	70.333333	96.0	109.156	1.017544	G
(X2, 3)	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
(X2, 4)	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	87.0	72	88	Very Good	70.0	True	82.333333	88.0	135.504	0.818182	V

x1x2.loc[len(x1x2.index)]=["Oliver", 87.0, 72, 88, "Very Good", 135.504, True, 0.818182, 95, 110.00, 1.01, "V"]

x1x2

	NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
(X1, 0)	Alice	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
(X1, 1)	Juliet	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
(X1, 2)	Alex	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
(X2, 3)	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
(X2, 4)	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V

data = [{"NAME": "Oliver", "STATISTICAL_INFERENCE": 87.0, "STATISTICAL_METHODS": 72, "VECTORS_&_MATRICES": 88, "REMARKS": "Very Good", "PYTHON": 135.504, "1ST": True, "2ND": 0.818182, "3RD": 95, "MULTIPLY": 110.00, "RATIO": 1.01, "Rem:Short": "V"}] 

x1x2 = x1x2.append(data, ignore_index=True, sort=False)
x1x2

	NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
7	Oliver	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V

data = [{"NAME": "Oliver", "STATISTICAL_INFERENCE": 87.0, "STATISTICAL_METHODS": 72, "VECTORS_&_MATRICES": 88, "REMARKS": "Very Good", "PYTHON": 13509, "1ST": True, "2ND": 0.818182, "3RD": 95, "MULTIPLY": 110.00, "RATIO": 1.01, "Rem:Short": "V"}] 

x1x2 = x1x2.append(data, ignore_index=False, sort=False)

x1x2

	NAME	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
7	Oliver	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

df = pd.DataFrame([[1, 2], [3, 4]], columns=list('AB'), index=['x', 'y'])
df

	A	B
x	1	2
y	3	4

df2 = pd.DataFrame([[5, 6], [7, 8]], columns=list('AB'), index=['x', 'y'])
df

	A	B
x	1	2
y	3	4

df.append(df2)

	A	B
x	1	2
y	3	4
x	5	6
y	7	8

df.append(df2, ignore_index=True)

	A	B
0	1	2
1	3	4
2	5	6
3	7	8

# Inserting column in any position
x1x2.insert(1, "D", 5) # Inplace opeartion

x1x2

	NAME	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
7	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

x1x2.insert(1, "D_new", [5, 5,55,5,60,30,20, 34, 35])
x1x2

	NAME	D_new	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	5	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	5	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	55	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	5	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	60	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	30	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	20	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
7	Oliver	34	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	35	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

x1x2["C"] = [10, 20, 30, 40, 100, 20, 1, 56, 45]
x1x2

	NAME	D_new	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short	C
0	Alice	5	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E	10
1	Juliet	5	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G	20
2	Alex	55	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G	30
3	Sara	5	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G	40
4	Oliver	60	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	100
5	Oliver	30	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	20
6	Oliver	20	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	1
7	Oliver	34	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	56
0	Oliver	35	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V	45

import numpy as np
x1x2.loc[:, "E"] = list(np.random.rand(9))
x1x2

	NAME	D_new	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short	C	E
0	Alice	5	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E	10	0.867215
1	Juliet	5	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G	20	0.033397
2	Alex	55	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G	30	0.091228
3	Sara	5	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G	40	0.820054
4	Oliver	60	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	100	0.337483
5	Oliver	30	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	20	0.511977
6	Oliver	20	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	1	0.034382
7	Oliver	34	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	56	0.478075
0	Oliver	35	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V	45	0.529336

x1x2_copy = x1x2.assign(G = x1x2.E * 100) # condition is column label should be single letter
x1x2_copy

	NAME	D_new	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short	C	E	G
0	Alice	5	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E	10	0.867215	86.721454
1	Juliet	5	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G	20	0.033397	3.339708
2	Alex	55	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G	30	0.091228	9.122837
3	Sara	5	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G	40	0.820054	82.005447
4	Oliver	60	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	100	0.337483	33.748330
5	Oliver	30	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V	20	0.511977	51.197651
6	Oliver	20	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	1	0.034382	3.438153
7	Oliver	34	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V	56	0.478075	47.807491
0	Oliver	35	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V	45	0.529336	52.933592

13. Duplicates removal

x1x2.drop(['D_new', 'C', 'E'], axis=1, inplace=True)
x1x2 

	NAME	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
7	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

x1x2_n = x1x2.copy()

x1x2.duplicated()

0    False
1    False
2    False
3    False
4    False
5    False
6    False
7     True
0    False
dtype: bool

x1x2 = x1x2[~x1x2.duplicated()]

x1x2

	NAME	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

# Remove duplicates
x1x2_n.drop_duplicates() # What is other techniques using  x1x2.duplicated()?

	NAME	D	STATISTICAL_INFERENCE	STATISTICAL_METHODS	VECTORS_&_MATRICES	REMARKS	PYTHON	1ST	2ND	3RD	MULTIPLY	RATIO	Rem:Short
0	Alice	5	87.0	94	92	Excellent	20.000	True	91.000000	94.0	176.908	1.021739	E
1	Juliet	5	NaN	87	74	Good	40.000	False	80.500000	87.0	163.734	1.175676	G
2	Alex	5	96.0	58	57	Good	50.000	True	70.333333	96.0	109.156	1.017544	G
3	Sara	5	65.0	63	96	Good	NaN	True	74.666667	96.0	118.566	0.656250	G
4	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
5	Oliver	5	87.0	72	88	Very Good	70.000	True	82.333333	88.0	135.504	0.818182	V
6	Oliver	5	87.0	72	88	Very Good	135.504	True	0.818182	95.0	110.000	1.010000	V
0	Oliver	5	87.0	72	88	Very Good	13509.000	True	0.818182	95.0	110.000	1.010000	V

References

a) Pandas documentations
b) Pandas tutorials