8/9/2020 pandas(set2)

In [4]:

import pandas as pd
file= pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/diamon
ds.csv')
file.head(10)

Out[4]:

carat cut color clarity depth table price x y z

0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43

1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31

2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31

3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63

4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

5 0.24 Very Good J VVS2 62.8 57.0 336 3.94 3.96 2.48

6 0.24 Very Good I VVS1 62.3 57.0 336 3.95 3.98 2.47

7 0.26 Very Good H SI1 61.9 55.0 337 4.07 4.11 2.53

8 0.22 Fair E VS2 65.1 61.0 337 3.87 3.78 2.49

9 0.23 Very Good H VS1 59.4 61.0 338 4.00 4.05 2.39

In [5]:

import pandas as pd
coloum = ['carat', 'cut', 'x', 'y', 'z']
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("First 6 rows:")
diamonds[coloum].head(6)

First 6 rows:

Out[5]:

carat cut x y z

0 0.23 Ideal 3.95 3.98 2.43

1 0.21 Premium 3.89 3.84 2.31

2 0.23 Good 4.05 4.07 2.31

3 0.29 Premium 4.20 4.23 2.63

4 0.31 Good 4.34 4.35 2.75

5 0.24 Very Good 3.94 3.96 2.48

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 1/10
8/9/2020 pandas(set2)

In [6]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print(diamonds['carat'])

0 0.23
1 0.21
2 0.23
3 0.29
4 0.31
...
53935 0.72
53936 0.72
53937 0.70
53938 0.86
53939 0.75
Name: carat, Length: 53940, dtype: float64

In [7]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
diamonds['Quality–color'] = diamonds.cut + ', ' + diamonds.color
diamonds.head(10)

Out[7]:

carat cut color clarity depth table price x y z Quality–color

0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43 Ideal, E

1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31 Premium, E

2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31 Good, E

3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63 Premium, I

4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75 Good, J

5 0.24 Very Good J VVS2 62.8 57.0 336 3.94 3.96 2.48 Very Good, J

6 0.24 Very Good I VVS1 62.3 57.0 336 3.95 3.98 2.47 Very Good, I

7 0.26 Very Good H SI1 61.9 55.0 337 4.07 4.11 2.53 Very Good, H

8 0.22 Fair E VS2 65.1 61.0 337 3.87 3.78 2.49 Fair, E

9 0.23 Very Good H VS1 59.4 61.0 338 4.00 4.05 2.39 Very Good, H

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 2/10
8/9/2020 pandas(set2)

In [8]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Number of rows and columns:")
print(diamonds.shape)
print("Data type of each column:")
print(diamonds.dtypes)

Number of rows and columns:

(53940, 10)
Data type of each column:
carat float64
cut object
color object
clarity object
depth float64
table float64
price int64
x float64
y float64
z float64
dtype: object

In [9]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nAfter renaming two of the columns of the diamond dataframe:")
diamonds.rename(columns={'color':'diamond_color', 'price':'dimaond_price'}, inplace=Tru
e)
diamonds.head()

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

After renaming two of the columns of the diamond dataframe:

Out[9]:

carat cut diamond_color clarity depth table dimaond_price x y z

0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43

1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31

2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31

3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63

4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 3/10
8/9/2020 pandas(set2)

In [10]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\n After removing multiple rows:")
diamonds.drop([1, 4, 5], inplace=True)
diamonds.head()

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

After removing multiple rows:

Out[10]:

carat cut color clarity depth table price x y z

0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43

2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31

3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63

6 0.24 Very Good I VVS1 62.3 57.0 336 3.95 3.98 2.47

7 0.26 Very Good H SI1 61.9 55.0 337 4.07 4.11 2.53

In [11]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\n After removing the second column of the Dataframe:")
diamonds.drop('cut',axis=1, inplace=True)
print(diamonds.head())

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

After removing the second column of the Dataframe:

carat color clarity depth table price x y z
0 0.23 E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 J SI2 63.3 58.0 335 4.34 4.35 2.75

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 4/10
8/9/2020 pandas(set2)

In [12]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\n cut Series in ascending order :")
x = diamonds.cut.sort_values(ascending=True)
print(x)

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

cut Series in ascending order :

3850 Fair
51464 Fair
51466 Fair
10237 Fair
10760 Fair
...
7402 Very Good
43101 Very Good
16893 Very Good
16898 Very Good
21164 Very Good
Name: cut, Length: 53940, dtype: object

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 5/10
8/9/2020 pandas(set2)

In [13]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nSort the entire diamonds DataFrame by the 'carat' Series in ascending order")
result = diamonds.sort_values('carat')
print(result)
print("\nSort the entire diamonds DataFrame by the 'carat' Series in descending order"
)
result = diamonds.sort_values('carat', ascending=False)
print(result)

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 6/10
8/9/2020 pandas(set2)

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

Sort the entire diamonds DataFrame by the 'carat' Series in ascending orde
r
carat cut color clarity depth table price x y
z
31593 0.20 Premium E VS2 61.1 59.0 367 3.81 3.78 2.
32
31597 0.20 Ideal D VS2 61.5 57.0 367 3.81 3.77 2.
33
31596 0.20 Premium F VS2 62.6 59.0 367 3.73 3.71 2.
33
31595 0.20 Ideal E VS2 59.7 55.0 367 3.86 3.84 2.
30
31594 0.20 Premium E VS2 59.7 62.0 367 3.84 3.80 2.
28
... ... ... ... ... ... ... ... ... ...
...
25999 4.01 Premium J I1 62.5 62.0 15223 10.02 9.94 6.
24
25998 4.01 Premium I I1 61.0 61.0 15223 10.14 10.10 6.
17
27130 4.13 Fair H I1 64.8 61.0 17329 10.00 9.85 6.
43
27630 4.50 Fair J I1 65.8 58.0 18531 10.23 10.16 6.
72
27415 5.01 Fair J I1 65.5 59.0 18018 10.74 10.54 6.
98

[53940 rows x 10 columns]

Sort the entire diamonds DataFrame by the 'carat' Series in descending or

der
carat cut color clarity depth table price x y
z
27415 5.01 Fair J I1 65.5 59.0 18018 10.74 10.54 6.
98
27630 4.50 Fair J I1 65.8 58.0 18531 10.23 10.16 6.
72
27130 4.13 Fair H I1 64.8 61.0 17329 10.00 9.85 6.
43
25999 4.01 Premium J I1 62.5 62.0 15223 10.02 9.94 6.
24
25998 4.01 Premium I I1 61.0 61.0 15223 10.14 10.10 6.
17
... ... ... ... ... ... ... ... ... ...
...
31592 0.20 Premium E VS2 59.0 60.0 367 3.81 3.78 2.
24
31591 0.20 Premium E VS2 59.8 62.0 367 3.79 3.77 2.
26
31601 0.20 Premium D VS2 61.7 60.0 367 3.77 3.72 2.
31
14 0.20 Premium E SI2 60.2 62.0 345 3.79 3.75 2.
27
localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 7/10
8/9/2020 pandas(set2)

31596 0.20 Premium F VS2 62.6 59.0 367 3.73 3.71 2.

33

[53940 rows x 10 columns]

In [14]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head(20))
print("\nRows to only show carat weight at least 0.3:")
booleans = []
for w in diamonds.carat:
if w >= .3:
booleans.append(True)
else:
booleans.append(False)
print(booleans[0:20])

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75
5 0.24 Very Good J VVS2 62.8 57.0 336 3.94 3.96 2.48
6 0.24 Very Good I VVS1 62.3 57.0 336 3.95 3.98 2.47
7 0.26 Very Good H SI1 61.9 55.0 337 4.07 4.11 2.53
8 0.22 Fair E VS2 65.1 61.0 337 3.87 3.78 2.49
9 0.23 Very Good H VS1 59.4 61.0 338 4.00 4.05 2.39
10 0.30 Good J SI1 64.0 55.0 339 4.25 4.28 2.73
11 0.23 Ideal J VS1 62.8 56.0 340 3.93 3.90 2.46
12 0.22 Premium F SI1 60.4 61.0 342 3.88 3.84 2.33
13 0.31 Ideal J SI2 62.2 54.0 344 4.35 4.37 2.71
14 0.20 Premium E SI2 60.2 62.0 345 3.79 3.75 2.27
15 0.32 Premium E I1 60.9 58.0 345 4.38 4.42 2.68
16 0.30 Ideal I SI2 62.0 54.0 348 4.31 4.34 2.68
17 0.30 Good J SI1 63.4 54.0 351 4.23 4.29 2.70
18 0.30 Good J SI1 63.8 56.0 351 4.23 4.26 2.71
19 0.30 Very Good J SI1 62.7 59.0 351 4.21 4.27 2.66

Rows to only show carat weight at least 0.3:

[False, False, False, False, True, False, False, False, False, False, Tru
e, False, False, True, False, True, True, True, True, True]

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 8/10
8/9/2020 pandas(set2)

In [15]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nDiamonds where length>5, width>5 and depth>5:")
result = diamonds[(diamonds.x>5) & (diamonds.y>5) & (diamonds.z>5)]
print(result.head())

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

Diamonds where length>5, width>5 and depth>5:

carat cut color clarity depth table price x y z
11778 1.83 Fair J I1 70.0 58.0 5083 7.34 7.28 5.12
13002 2.14 Fair J I1 69.4 57.0 5405 7.74 7.70 5.36
13118 2.15 Fair J I1 65.5 57.0 5430 8.01 7.95 5.23
13562 1.96 Fair F I1 66.6 60.0 5554 7.59 7.56 5.04
13757 2.22 Fair J I1 66.7 56.0 5607 8.04 8.02 5.36

In [16]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nDrop all non-numeric columns of diamonds DataFrame:")
print(diamonds.dtypes)

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

Drop all non-numeric columns of diamonds DataFrame:

carat float64
cut object
color object
clarity object
depth float64
table float64
price int64
x float64
y float64
z float64
dtype: object

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 9/10
8/9/2020 pandas(set2)

In [17]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nMean of each numeric column of diamonds DataFrame:")
print(diamonds.mean())

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

Mean of each numeric column of diamonds DataFrame:

carat 0.797940
depth 61.749405
table 57.457184
price 3932.799722
x 5.731157
y 5.734526
z 3.538734
dtype: float64

In [18]:

import pandas as pd
diamonds = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/d
iamonds.csv')
print("Original Dataframe:")
print(diamonds.head())
print("\nCount, minimum, maximum price for each cut of diamonds DataFrame:")
print(diamonds.groupby('cut').price.agg(['count', 'min', 'max']))

Original Dataframe:
carat cut color clarity depth table price x y z
0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43
1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31
2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31
3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63
4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

Count, minimum, maximum price for each cut of diamonds DataFrame:

count min max
cut
Fair 1610 337 18574
Good 4906 327 18788
Ideal 21551 326 18806
Premium 13791 326 18823
Very Good 12082 336 18818

In [ ]:

localhost:8888/nbconvert/html/pandas(set2).ipynb?download=false 10/10