Tuesday, 30 June 2020

Python : Pandas - 2



import numpy as np
import pandas as pd​
# Random Dataframe​
df1 = pd.DataFrame(np.random.randn(10,5), columns = ['A','B','C','D','E'])​
. . .

a1 = np.random.randn(10,5)​
print(type(a1))
print(a1)
<class 'numpy.ndarray'>
[[ 0.18659011  0.32508505 -0.34342072 -0.33952857 -0.48199335]
 [-1.25637213  1.69819355 -1.9301858  -0.17224627  2.17514008]
 [-0.31058854 -0.01588517 -1.1138929  -0.5838138   0.83741961]
 [-0.4123694  -0.89220464 -1.4258579   1.51079098  1.20191611]
 [ 0.06600725  2.45458766  1.37562926 -1.98480044 -1.62700227]
 [-1.53102481 -0.79509763 -1.01322225  0.33331608  0.47981504]
 [-0.15095467 -0.46888199  1.22936127  0.08834043 -1.59052134]
 [ 0.84350394 -1.70928615  0.32424964 -0.21524692  0.38015035]
 [ 1.86117202 -0.86295479 -1.31786209  1.53286495 -1.14890751]
 [ 1.22011683  0.55062625 -0.93297329 -0.59828361  0.52727458]]
. . .

# Creating and writing into csv file.
df1.to_csv('C:/Users/kuldip_s/Documents/Python Scripts/random_data_csv.csv',sep=',',index = False) # by default Index is True
​
. . .
 # Creating and writing into excel file.
df1.to_excel('C:/Users/kuldip_s/Documents/Python Scripts/random_data_excel.xlsx',sheet_name='First_Sheet')
. . .

df2 = pd.read_csv('C:/Users/kuldip_s/Documents/Python Scripts/random_data_csv.csv')
print(df2)
df3 = pd.read_csv('C:/Users/kuldip_s/Documents/Python Scripts/random_data_csv.csv',sep=",", header=0)
print(df3)
          A         B         C         D         E
0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1  0.458764 -1.265745  0.090432  1.785799  0.034077
2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6  0.889480  0.020148  0.354449 -1.041984  1.167718
7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
          A         B         C         D         E
0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1  0.458764 -1.265745  0.090432  1.785799  0.034077
2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6  0.889480  0.020148  0.354449 -1.041984  1.167718
7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
. . .
 df2 = pd.read_excel('C:/Users/kuldip_s/Documents/Python Scripts/random_data_excel.xlsx')
df3 = pd.read_excel('C:/Users/kuldip_s/Documents/Python Scripts/random_data_excel.xlsx','First_Sheet')
df4 = pd.read_excel('C:/Users/kuldip_s/Documents/Python Scripts/random_data_excel.xlsx','First_Sheet', index_col=0)
​
print('------------------------with no additional parameter---------')
print(df2)
print('------------------------printing 1st sheet ---------')
print(df3)
print('------------------------printing without index ---------')
print(df4)
print('------------------------printing without index ---------')
print(df4)​
​


------------------------with no additional parameter---------
   Unnamed: 0         A         B         C         D         E
0           0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1           1  0.458764 -1.265745  0.090432  1.785799  0.034077
2           2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3           3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4           4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5           5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6           6  0.889480  0.020148  0.354449 -1.041984  1.167718
7           7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8           8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9           9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
------------------------printing 1st sheet ---------
   Unnamed: 0         A         B         C         D         E
0           0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1           1  0.458764 -1.265745  0.090432  1.785799  0.034077
2           2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3           3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4           4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5           5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6           6  0.889480  0.020148  0.354449 -1.041984  1.167718
7           7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8           8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9           9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
------------------------printing without index ---------
          A         B         C         D         E
0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1  0.458764 -1.265745  0.090432  1.785799  0.034077
2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6  0.889480  0.020148  0.354449 -1.041984  1.167718
7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
------------------------printing without index ---------
          A         B         C         D         E
0  1.373988 -0.695397 -1.561186  0.365325  0.867092
1  0.458764 -1.265745  0.090432  1.785799  0.034077
2 -0.330147  0.691178  1.928890 -0.555014 -0.163378
3 -0.737117  0.400541 -0.164102 -0.450007 -0.601012
4  1.331716  0.291633 -0.736913 -0.695256  0.801779
5 -0.577260  0.849215 -0.069959  0.397717  1.528757
6  0.889480  0.020148  0.354449 -1.041984  1.167718
7  2.455193 -0.534589 -0.589731  0.923948 -0.814283
8 -0.908036 -0.101546 -1.303603  0.319622  1.520226
9 -0.232327  0.030451  0.366966 -0.996714 -1.617141
. . .

cars = pd.read_excel('C:/Users/kuldip_s/Documents/Python Scripts/mtcars set.xlsx')
print(cars)
             Unnamed: 0   mpg  cyl   disp   hp  drat     wt   qsec  vs  am  \
0             Mazda RX4  21.0    6  160.0  110  3.90  2.620  16.46   0   1  
1         Mazda RX4 Wag  21.0    6  160.0  110  3.90  2.875  17.02   0   1  
2            Datsun 710  22.8    4  108.0   93  3.85  2.320  18.61   1   1  
3        Hornet 4 Drive  21.4    6  258.0  110  3.08  3.215  19.44   1   0  
4     Hornet Sportabout  18.7    8  360.0  175  3.15  3.440  17.02   0   0  
5               Valiant  18.1    6  225.0  105  2.76  3.460  20.22   1   0  
6            Duster 360  14.3    8  360.0  245  3.21  3.570  15.84   0   0  
7             Merc 240D  24.4    4  146.7   62  3.69  3.190  20.00   1   0  
8              Merc 230  22.8    4  140.8   95  3.92  3.150  22.90   1   0  
9              Merc 280  19.2    6  167.6  123  3.92  3.440  18.30   1   0  
10            Merc 280C  17.8    6  167.6  123  3.92  3.440  18.90   1   0  
11           Merc 450SE  16.4    8  275.8  180  3.07  4.070  17.40   0   0  
12           Merc 450SL  17.3    8  275.8  180  3.07  3.730  17.60   0   0  
13          Merc 450SLC  15.2    8  275.8  180  3.07  3.780  18.00   0   0  
14   Cadillac Fleetwood  10.4    8  472.0  205  2.93  5.250  17.98   0   0  
15  Lincoln Continental  10.4    8  460.0  215  3.00  5.424  17.82   0   0  
16    Chrysler Imperial  14.7    8  440.0  230  3.23  5.345  17.42   0   0  
17             Fiat 128  32.4    4   78.7   66  4.08  2.200  19.47   1   1  
18          Honda Civic  30.4    4   75.7   52  4.93  1.615  18.52   1   1  
19       Toyota Corolla  33.9    4   71.1   65  4.22  1.835  19.90   1   1  
20        Toyota Corona  21.5    4  120.1   97  3.70  2.465  20.01   1   0  
21     Dodge Challenger  15.5    8  318.0  150  2.76  3.520  16.87   0   0  
22          AMC Javelin  15.2    8  304.0  150  3.15  3.435  17.30   0   0  
23           Camaro Z28  13.3    8  350.0  245  3.73  3.840  15.41   0   0  
24     Pontiac Firebird  19.2    8  400.0  175  3.08  3.845  17.05   0   0  
25            Fiat X1-9  27.3    4   79.0   66  4.08  1.935  18.90   1   1  
26        Porsche 914-2  26.0    4  120.3   91  4.43  2.140  16.70   0   1  
27         Lotus Europa  30.4    4   95.1  113  3.77  1.513  16.90   1   1  
28       Ford Pantera L  15.8    8  351.0  264  4.22  3.170  14.50   0   1  
29         Ferrari Dino  19.7    6  145.0  175  3.62  2.770  15.50   0   1  
30        Maserati Bora  15.0    8  301.0  335  3.54  3.570  14.60   0   1  
31           Volvo 142E  21.4    4  121.0  109  4.11  2.780  18.60   1   1  

    gear  carb 
0      4     4 
1      4     4 
2      4     1 
3      3     1 
4      3     2 
5      3     1 
6      3     4 
7      4     2 
8      4     2 
9      4     4 
10     4     4 
11     3     3 
12     3     3 
13     3     3 
14     3     4 
15     3     4 
16     3     4 
17     4     1 
18     4     2 
19     4     1 
20     3     1 
21     3     2 
22     3     2 
23     3     4 
24     3     2 
25     4     1 
26     5     2 
27     5     2 
28     5     4 
29     5     6 
30     5     8 
31     4     2 
. . .

cars.head()  # by default first 5 rows
Out[8]:
Unnamed: 0
mpg
cyl
disp
hp
drat
wt
qsec
vs
am
gear
carb
0
Mazda RX4
21.0
6
160.0
110
3.90
2.620
16.46
0
1
4
4
1
Mazda RX4 Wag
21.0
6
160.0
110
3.90
2.875
17.02
0
1
4
4
2
Datsun 710
22.8
4
108.0
93
3.85
2.320
18.61
1
1
4
1
3
Hornet 4 Drive
21.4
6
258.0
110
3.08
3.215
19.44
1
0
3
1
4
Hornet Sportabout
18.7
8
360.0
175
3.15
3.440
17.02
0
0
3
2
. . .

cars.tail()
Out[9]:
Unnamed: 0
mpg
cyl
disp
hp
drat
wt
qsec
vs
am
gear
carb
27
Lotus Europa
30.4
4
95.1
113
3.77
1.513
16.9
1
1
5
2
28
Ford Pantera L
15.8
8
351.0
264
4.22
3.170
14.5
0
1
5
4
29
Ferrari Dino
19.7
6
145.0
175
3.62
2.770
15.5
0
1
5
6
30
Maserati Bora
15.0
8
301.0
335
3.54
3.570
14.6
0
1
5
8
31
Volvo 142E
21.4
4
121.0
109
4.11
2.780
18.6
1
1
4
2
. . .

cars.head(10)
Out[10]:
Unnamed: 0
mpg
cyl
disp
hp
drat
wt
qsec
vs
am
gear
carb
0
Mazda RX4
21.0
6
160.0
110
3.90
2.620
16.46
0
1
4
4
1
Mazda RX4 Wag
21.0
6
160.0
110
3.90
2.875
17.02
0
1
4
4
2
Datsun 710
22.8
4
108.0
93
3.85
2.320
18.61
1
1
4
1
3
Hornet 4 Drive
21.4
6
258.0
110
3.08
3.215
19.44
1
0
3
1
4
Hornet Sportabout
18.7
8
360.0
175
3.15
3.440
17.02
0
0
3
2
5
Valiant
18.1
6
225.0
105
2.76
3.460
20.22
1
0
3
1
6
Duster 360
14.3
8
360.0
245
3.21
3.570
15.84
0
0
3
4
7
Merc 240D
24.4
4
146.7
62
3.69
3.190
20.00
1
0
4
2
8
Merc 230
22.8
4
140.8
95
3.92
3.150
22.90
1
0
4
2
9
Merc 280
19.2
6
167.6
123
3.92
3.440
18.30
1
0
4
4
. . .

a1=cars.head(10)
a1.tail(3)
Out[11]:
Unnamed: 0
mpg
cyl
disp
hp
drat
wt
qsec
vs
am
gear
carb
7
Merc 240D
24.4
4
146.7
62
3.69
3.19
20.0
1
0
4
2
8
Merc 230
22.8
4
140.8
95
3.92
3.15
22.9
1
0
4
2
9
Merc 280
19.2
6
167.6
123
3.92
3.44
18.3
1
0
4
4













. . .
 # View number of rows and columns in a dataframe
cars.shape
Out[12]:
(32, 12)
. . .
 # print consize summary info of columns
cars.info(null_counts=True)
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32 entries, 0 to 31
Data columns (total 12 columns):
Unnamed: 0    32 non-null object
mpg           32 non-null float64
cyl           32 non-null int64
disp          32 non-null float64
hp            32 non-null int64
drat          32 non-null float64
wt            32 non-null float64
qsec          32 non-null float64
vs            32 non-null int64
am            32 non-null int64
gear          32 non-null int64
carb          32 non-null int64
dtypes: float64(5), int64(6), object(1)
memory usage: 3.1+ KB
. . .

cars.mean()
Out[14]:

mpg      20.090625
cyl       6.187500
disp    230.721875
hp      146.687500
drat      3.596563
wt        3.217250
qsec     17.848750
vs        0.437500
am        0.406250
gear      3.687500
carb      2.812500
dtype: float64
. . .

cars.median()
Out[15]:
mpg      19.200
cyl       6.000
disp    196.300
hp      123.000
drat      3.695
wt        3.325
qsec     17.710
vs        0.000
am        0.000
gear      4.000
carb      2.000
dtype: float64

. . .
 cars.std()
Out[16]:
mpg       6.026948
cyl       1.785922
disp    123.938694
hp       68.562868
drat      0.534679
wt        0.978457
qsec      1.786943
vs        0.504016
am        0.498991
gear      0.737804
carb      1.615200
dtype: float64
. . .

cars.max()
Out[17]:
Unnamed: 0    Volvo 142E
mpg                 33.9
cyl                    8
disp                 472
hp                   335
drat                4.93
wt                 5.424
qsec                22.9
vs                     1
am                     1
gear                   5
carb                   8
dtype: object
. . .

cars.count()
Out[18]:
Unnamed: 0    32
mpg           32
cyl           32
disp          32
hp            32
drat          32
wt            32
qsec          32
vs            32
am            32
gear          32
carb          32
dtype: int64


at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)