[2]
0 s
import pandas as pd
# Crear tabla llamada df
df = pd.DataFrame()
# crea una columna numeros
df ['numeros'] = [1, 2, 3, 4]
# columna letras
df['letras'] = ['a', 'b', 'c', 'd']
output
[ ]
# muestra la columna numeros
df['numeros']
output
0 1
1 2
2 3
3 4
Name: numeros, dtype: int64
[ ]
# DataFrame: tabla de datos
# Series: serie de datos
type(df), type(df['numeros'])
output
(pandas.core.frame.DataFrame, pandas.core.series.Series)
[ ]
# crea una columna cuadrada con los
# valores de la columna numeros al cuadrado
df['cuadrados'] = df['numeros'] ** 2
df
output
[ ]
acumulados = [] # una lista vacia
suma = 0 # una suma en cero
for i in df['numeros']: # para cada dato i en la columna de numeros
suma = suma + i # suma e i se adicionan y el resultado va a suma
acumulados.append(suma) # agreaga suma a la lista
[ ]
# metodo cumsum de pd.Series
df['numeros'].cumsum()
output
0 1
1 3
2 6
3 10
Name: numeros, dtype: int64
[ ]
# conversion a lista
df['numeros'].cumsum().tolist()
output
[1, 3, 6, 10]
[ ]
# nueva columna de tabla con el nombre acumulados
df['acumulados'] = df['numeros'].cumsum()
df
output
[59]
0 s
# Lee el archivo CSV desde Google Drive
df = pd.read_csv("/content/drive/MyDrive/Python/Proy_1/bodyPerformance.csv", sep=';')
[60]
0 s
print(df.head(100))
output
age,gender,height_cm,weight_kg,body fat_%,diastolic,systolic,gripForce,sit and bend forward_cm,sit-ups counts,broad jump_cm,class
0 27.0,M,172.3,75.24,21.3,80.0,130.0,54.9,18.4,6...
1 25.0,M,165.0,55.8,15.7,77.0,126.0,36.4,16.3,53...
2 31.0,M,179.6,78.0,20.1,92.0,152.0,44.8,12.0,49...
3 32.0,M,174.5,71.1,18.4,76.0,147.0,41.4,15.2,53...
4 28.0,M,173.8,67.7,17.1,70.0,127.0,43.5,27.1,45...
5 36.0,F,165.4,55.4,22.0,64.0,119.0,23.8,21.0,27...
6 42.0,F,164.5,63.7,32.2,72.0,135.0,22.7,0.8,18....
7 33.0,M,174.9,77.2,36.9,84.0,137.0,45.9,12.3,42...
8 54.0,M,166.8,67.5,27.6,85.0,165.0,40.4,18.6,34...
9 28.0,M,185.0,84.6,14.4,81.0,156.0,57.9,12.1,55...
10 42.0,M,169.2,65.4,19.3,63.0,110.0,43.5,16.0,68...
11 57.0,F,153.0,49.0,20.9,69.0,106.0,21.5,30.0,0....
12 27.0,F,156.0,53.9,35.5,69.0,116.0,23.1,13.1,28...
13 22.0,M,175.7,67.9,11.3,71.0,103.0,52.5,19.2,55...
14 24.0,M,181.0,84.4,20.4,80.0,120.0,48.9,7.2,54....
15 45.0,F,159.0,63.1,30.9,93.0,144.0,34.1,19.0,30...
16 25.0,F,164.2,66.6,30.2,82.0,120.0,25.7,22.9,39...
17 26.0,M,179.9,71.5,9.7,64.0,135.0,59.6,17.8,61....
18 26.0,M,169.2,70.6,21.0,63.0,129.0,41.3,15.1,53...
19 21.0,F,162.7,47.2,18.9,78.0,133.0,25.4,20.5,36...
20 25.0,F,161.7,63.36,31.3,89.0,128.0,25.0,10.7,3...
21 59.0,F,155.9,62.7,30.2,76.0,143.0,36.8,29.1,25...
22 38.0,M,166.7,67.3,23.2,70.0,111.0,26.1,19.7,62...
23 44.0,M,170.0,63.3,12.9,65.0,115.0,44.5,11.6,49...
24 23.0,F,164.1,59.4,29.6,91.0,126.0,24.6,27.5,32...
25 62.0,M,169.0,70.7,30.5,96.0,146.0,39.3,4.0,43....
26 47.0,F,158.3,53.5,29.2,70.0,117.0,25.9,8.1,32....
27 48.0,M,175.8,84.5,31.4,83.0,125.0,33.8,3.7,24....
28 36.0,M,176.0,81.3,24.5,81.0,139.0,46.2,8.1,54....
29 50.0,F,159.8,57.1,24.4,63.0,103.0,30.8,24.4,30...
30 25.0,M,170.9,70.7,15.7,80.0,127.0,36.4,26.4,38...
31 26.0,M,176.7,77.2,16.3,66.0,129.0,50.0,9.1,51....
32 28.0,F,159.5,51.54,24.5,82.0,123.0,37.2,23.0,3...
33 30.0,M,172.1,79.5,26.7,91.0,148.0,34.7,-2.0,40...
34 49.0,F,151.5,52.0,27.6,77.0,144.0,23.8,21.3,39...
35 40.0,M,177.6,88.6,20.3,93.0,138.0,51.5,12.1,54...
36 21.0,M,172.5,66.4,12.5,82.0,130.0,51.2,6.3,46....
37 31.0,M,177.5,79.5,23.0,90.0,148.0,51.2,18.4,62...
38 32.0,M,178.0,84.5,21.2,68.0,130.0,52.3,16.2,62...
39 27.0,M,177.6,79.7,22.8,59.0,108.0,48.0,1.8,59....
40 42.0,M,168.0,61.0,14.9,94.0,151.0,28.9,1.0,32....
41 52.0,M,173.6,84.9,30.3,93.0,144.0,42.0,9.0,43....
42 39.0,M,173.3,69.8,23.8,76.0,137.0,40.0,18.2,38...
43 33.0,F,159.6,60.5,32.1,62.0,106.0,21.9,22.2,24...
44 25.0,F,161.8,57.7,21.7,74.0,115.0,29.3,26.6,50...
45 31.0,M,169.9,73.1,19.2,97.0,145.0,45.0,14.5,37...
46 34.0,M,183.6,76.82,16.3,80.0,120.0,46.3,14.2,5...
47 26.0,M,172.1,66.1,24.9,62.0,102.0,19.9,-9.9,44...
48 28.0,M,180.1,82.1,15.0,83.0,147.0,52.6,18.8,55...
49 58.0,M,164.2,64.0,19.8,93.0,150.0,36.8,18.3,38...
50 48.0,M,169.8,75.4,14.7,94.0,149.0,51.4,24.7,55...
51 23.0,M,180.1,65.9,14.4,72.0,130.0,45.4,18.1,56...
52 38.0,F,157.2,51.7,27.3,64.0,106.0,25.1,14.7,19...
53 43.0,F,168.3,69.3,31.9,88.0,139.0,32.1,20.2,33...
54 21.0,F,159.5,51.3,35.8,80.0,122.0,16.6,2.1,5.0...
55 56.0,M,166.7,56.9,16.5,90.0,147.0,41.6,17.8,30...
56 24.0,M,164.4,66.2,17.1,63.0,110.0,40.2,16.2,43...
57 58.0,F,146.5,46.4,32.9,71.0,127.0,18.7,17.4,20...
58 42.0,M,174.1,103.1,30.5,78.0,123.0,50.7,3.6,25...
59 45.0,M,185.4,80.0,21.9,93.0,144.0,46.2,7.1,22....
60 37.0,M,168.9,78.8,23.4,88.0,144.0,42.1,20.9,47...
61 31.0,M,175.3,83.6,30.1,93.0,152.0,45.9,7.2,55....
62 43.0,F,164.0,50.8,22.4,88.0,124.0,24.0,13.5,28...
63 23.0,F,162.4,58.9,29.6,71.0,119.0,28.1,25.5,48...
64 59.0,F,165.0,63.7,31.4,77.0,120.0,20.8,25.5,30...
65 63.0,M,166.6,75.5,31.6,62.0,122.0,34.1,6.7,17....
66 40.0,M,174.2,77.6,17.8,85.0,133.0,49.5,12.1,48...
67 27.0,F,150.5,55.7,39.6,66.0,114.0,29.7,13.4,23...
68 56.0,F,160.2,62.4,33.3,67.0,103.0,28.8,20.7,15...
69 35.0,M,179.0,75.0,10.7,74.0,129.0,47.7,16.6,54...
70 30.0,M,172.7,78.0,26.6,79.0,140.0,36.9,3.4,25....
71 56.0,M,160.2,62.7,30.2,85.0,140.0,35.4,9.5,27....
72 36.0,M,171.5,80.5,21.5,86.0,153.0,46.7,16.8,53...
73 60.0,M,175.1,66.5,17.3,85.0,125.0,40.4,13.9,31...
74 22.0,M,172.2,70.6,24.3,70.0,118.0,36.7,9.8,50....
75 22.0,M,171.9,78.46,22.9,64.0,116.0,43.6,-9.3,4...
76 37.0,M,174.0,75.2,18.5,82.0,142.0,39.7,20.5,50...
77 21.0,F,158.1,53.6,27.63524,70.0,115.0,18.9,12....
78 21.0,M,170.4,74.3,19.5,82.0,157.0,45.6,12.7,54...
79 60.0,F,158.6,62.7,34.6,80.0,137.0,29.3,18.4,12...
80 27.0,F,168.5,64.2,26.2,76.0,108.0,25.2,23.1,18...
81 59.0,F,156.3,60.5,33.6,79.0,130.0,29.6,22.4,23...
82 47.0,F,157.0,54.1,26.8,72.0,117.0,25.1,18.2,25...
83 21.0,F,161.3,50.6,23.5,69.0,127.0,27.5,29.4,39...
84 51.0,M,177.0,68.7,18.3,84.0,140.0,39.3,11.3,35...
85 48.0,M,171.0,66.2,17.3,99.0,144.0,48.8,16.0,49...
86 49.0,M,170.0,66.2,18.0,82.0,130.0,39.5,20.0,39...
87 41.0,F,158.1,51.0,21.7,86.0,127.0,23.1,28.6,46...
88 24.0,F,159.0,45.5,24.5,85.0,135.0,28.5,22.9,57...
89 35.0,M,178.4,79.0,15.4,73.0,127.0,52.7,14.7,68...
90 26.0,F,156.7,56.3,32.8,78.0,123.0,19.7,22.9,28...
91 35.0,M,178.5,78.4,13.8,81.0,136.0,51.5,17.1,64...
92 25.0,M,171.2,65.1,11.8,67.0,127.0,45.1,22.2,54...
93 30.0,M,176.4,71.7,17.9,68.0,130.0,53.4,24.3,56...
94 27.0,M,175.4,86.4,19.8,76.0,135.0,47.6,20.6,48...
95 41.0,M,166.7,65.7,21.5,90.0,151.0,49.6,18.7,54...
96 50.0,F,158.4,57.2,32.0,69.0,134.0,21.1,18.6,17...
97 22.0,M,175.8,72.0,30.4,75.0,115.0,34.6,19.0,54...
98 56.0,M,173.0,70.9,19.5,83.0,135.0,47.9,11.1,44...
99 46.0,F,159.1,52.2,27.2,84.0,127.0,22.9,17.9,30...
[68]
0 s
from io import StringIO # Importa StringIO desde el módulo io
# Datos en formato CSV
df_csv = """
age,gender,height_cm,weight_kg,body fat_%,diastolic,systolic,gripForce,sit and bend forward_cm,sit-ups counts,broad jump_cm,class
0 27.0,M,172.3,75.24,21.3,80.0,130.0,54.9,18.4,6...
1 25.0,M,165.0,55.8,15.7,77.0,126.0,36.4,16.3,53...
2 31.0,M,179.6,78.0,20.1,92.0,152.0,44.8,12.0,49...
3 32.0,M,174.5,71.1,18.4,76.0,147.0,41.4,15.2,53...
4 28.0,M,173.8,67.7,17.1,70.0,127.0,43.5,27.1,45...
5 36.0,F,165.4,55.4,22.0,64.0,119.0,23.8,21.0,27...
6 42.0,F,164.5,63.7,32.2,72.0,135.0,22.7,0.8,18....
7 33.0,M,174.9,77.2,36.9,84.0,137.0,45.9,12.3,42...
8 54.0,M,166.8,67.5,27.6,85.0,165.0,40.4,18.6,34...
9 28.0,M,185.0,84.6,14.4,81.0,156.0,57.9,12.1,55...
10 42.0,M,169.2,65.4,19.3,63.0,110.0,43.5,16.0,68...
11 57.0,F,153.0,49.0,20.9,69.0,106.0,21.5,30.0,0....
12 27.0,F,156.0,53.9,35.5,69.0,116.0,23.1,13.1,28...
13 22.0,M,175.7,67.9,11.3,71.0,103.0,52.5,19.2,55...
14 24.0,M,181.0,84.4,20.4,80.0,120.0,48.9,7.2,54....
15 45.0,F,159.0,63.1,30.9,93.0,144.0,34.1,19.0,30...
16 25.0,F,164.2,66.6,30.2,82.0,120.0,25.7,22.9,39...
17 26.0,M,179.9,71.5,9.7,64.0,135.0,59.6,17.8,61....
18 26.0,M,169.2,70.6,21.0,63.0,129.0,41.3,15.1,53...
19 21.0,F,162.7,47.2,18.9,78.0,133.0,25.4,20.5,36...
20 25.0,F,161.7,63.36,31.3,89.0,128.0,25.0,10.7,3...
21 59.0,F,155.9,62.7,30.2,76.0,143.0,36.8,29.1,25...
22 38.0,M,166.7,67.3,23.2,70.0,111.0,26.1,19.7,62...
23 44.0,M,170.0,63.3,12.9,65.0,115.0,44.5,11.6,49...
24 23.0,F,164.1,59.4,29.6,91.0,126.0,24.6,27.5,32...
25 62.0,M,169.0,70.7,30.5,96.0,146.0,39.3,4.0,43....
26 47.0,F,158.3,53.5,29.2,70.0,117.0,25.9,8.1,32....
27 48.0,M,175.8,84.5,31.4,83.0,125.0,33.8,3.7,24....
28 36.0,M,176.0,81.3,24.5,81.0,139.0,46.2,8.1,54....
29 50.0,F,159.8,57.1,24.4,63.0,103.0,30.8,24.4,30...
30 25.0,M,170.9,70.7,15.7,80.0,127.0,36.4,26.4,38...
31 26.0,M,176.7,77.2,16.3,66.0,129.0,50.0,9.1,51....
32 28.0,F,159.5,51.54,24.5,82.0,123.0,37.2,23.0,3...
33 30.0,M,172.1,79.5,26.7,91.0,148.0,34.7,-2.0,40...
34 49.0,F,151.5,52.0,27.6,77.0,144.0,23.8,21.3,39...
35 40.0,M,177.6,88.6,20.3,93.0,138.0,51.5,12.1,54...
36 21.0,M,172.5,66.4,12.5,82.0,130.0,51.2,6.3,46....
37 31.0,M,177.5,79.5,23.0,90.0,148.0,51.2,18.4,62...
38 32.0,M,178.0,84.5,21.2,68.0,130.0,52.3,16.2,62...
39 27.0,M,177.6,79.7,22.8,59.0,108.0,48.0,1.8,59....
40 42.0,M,168.0,61.0,14.9,94.0,151.0,28.9,1.0,32....
41 52.0,M,173.6,84.9,30.3,93.0,144.0,42.0,9.0,43....
42 39.0,M,173.3,69.8,23.8,76.0,137.0,40.0,18.2,38...
43 33.0,F,159.6,60.5,32.1,62.0,106.0,21.9,22.2,24...
44 25.0,F,161.8,57.7,21.7,74.0,115.0,29.3,26.6,50...
45 31.0,M,169.9,73.1,19.2,97.0,145.0,45.0,14.5,37...
46 34.0,M,183.6,76.82,16.3,80.0,120.0,46.3,14.2,5...
47 26.0,M,172.1,66.1,24.9,62.0,102.0,19.9,-9.9,44...
48 28.0,M,180.1,82.1,15.0,83.0,147.0,52.6,18.8,55...
49 58.0,M,164.2,64.0,19.8,93.0,150.0,36.8,18.3,38...
50 48.0,M,169.8,75.4,14.7,94.0,149.0,51.4,24.7,55...
51 23.0,M,180.1,65.9,14.4,72.0,130.0,45.4,18.1,56...
52 38.0,F,157.2,51.7,27.3,64.0,106.0,25.1,14.7,19...
53 43.0,F,168.3,69.3,31.9,88.0,139.0,32.1,20.2,33...
54 21.0,F,159.5,51.3,35.8,80.0,122.0,16.6,2.1,5.0...
55 56.0,M,166.7,56.9,16.5,90.0,147.0,41.6,17.8,30...
56 24.0,M,164.4,66.2,17.1,63.0,110.0,40.2,16.2,43...
57 58.0,F,146.5,46.4,32.9,71.0,127.0,18.7,17.4,20...
58 42.0,M,174.1,103.1,30.5,78.0,123.0,50.7,3.6,25...
59 45.0,M,185.4,80.0,21.9,93.0,144.0,46.2,7.1,22....
60 37.0,M,168.9,78.8,23.4,88.0,144.0,42.1,20.9,47...
61 31.0,M,175.3,83.6,30.1,93.0,152.0,45.9,7.2,55....
62 43.0,F,164.0,50.8,22.4,88.0,124.0,24.0,13.5,28...
63 23.0,F,162.4,58.9,29.6,71.0,119.0,28.1,25.5,48...
64 59.0,F,165.0,63.7,31.4,77.0,120.0,20.8,25.5,30...
65 63.0,M,166.6,75.5,31.6,62.0,122.0,34.1,6.7,17....
66 40.0,M,174.2,77.6,17.8,85.0,133.0,49.5,12.1,48...
67 27.0,F,150.5,55.7,39.6,66.0,114.0,29.7,13.4,23...
68 56.0,F,160.2,62.4,33.3,67.0,103.0,28.8,20.7,15...
69 35.0,M,179.0,75.0,10.7,74.0,129.0,47.7,16.6,54...
70 30.0,M,172.7,78.0,26.6,79.0,140.0,36.9,3.4,25....
71 56.0,M,160.2,62.7,30.2,85.0,140.0,35.4,9.5,27....
72 36.0,M,171.5,80.5,21.5,86.0,153.0,46.7,16.8,53...
73 60.0,M,175.1,66.5,17.3,85.0,125.0,40.4,13.9,31...
74 22.0,M,172.2,70.6,24.3,70.0,118.0,36.7,9.8,50....
75 22.0,M,171.9,78.46,22.9,64.0,116.0,43.6,-9.3,4...
76 37.0,M,174.0,75.2,18.5,82.0,142.0,39.7,20.5,50...
77 21.0,F,158.1,53.6,27.63524,70.0,115.0,18.9,12....
78 21.0,M,170.4,74.3,19.5,82.0,157.0,45.6,12.7,54...
79 60.0,F,158.6,62.7,34.6,80.0,137.0,29.3,18.4,12...
80 27.0,F,168.5,64.2,26.2,76.0,108.0,25.2,23.1,18...
81 59.0,F,156.3,60.5,33.6,79.0,130.0,29.6,22.4,23...
82 47.0,F,157.0,54.1,26.8,72.0,117.0,25.1,18.2,25...
83 21.0,F,161.3,50.6,23.5,69.0,127.0,27.5,29.4,39...
84 51.0,M,177.0,68.7,18.3,84.0,140.0,39.3,11.3,35...
85 48.0,M,171.0,66.2,17.3,99.0,144.0,48.8,16.0,49...
86 49.0,M,170.0,66.2,18.0,82.0,130.0,39.5,20.0,39...
87 41.0,F,158.1,51.0,21.7,86.0,127.0,23.1,28.6,46...
88 24.0,F,159.0,45.5,24.5,85.0,135.0,28.5,22.9,57...
89 35.0,M,178.4,79.0,15.4,73.0,127.0,52.7,14.7,68...
90 26.0,F,156.7,56.3,32.8,78.0,123.0,19.7,22.9,28...
91 35.0,M,178.5,78.4,13.8,81.0,136.0,51.5,17.1,64...
92 25.0,M,171.2,65.1,11.8,67.0,127.0,45.1,22.2,54...
93 30.0,M,176.4,71.7,17.9,68.0,130.0,53.4,24.3,56...
94 27.0,M,175.4,86.4,19.8,76.0,135.0,47.6,20.6,48...
95 41.0,M,166.7,65.7,21.5,90.0,151.0,49.6,18.7,54...
96 50.0,F,158.4,57.2,32.0,69.0,134.0,21.1,18.6,17...
97 22.0,M,175.8,72.0,30.4,75.0,115.0,34.6,19.0,54...
98 56.0,M,173.0,70.9,19.5,83.0,135.0,47.9,11.1,44...
99 46.0,F,159.1,52.2,27.2,84.0,127.0,22.9,17.9,30... """
# Crea un DataFrame con los datos
df = pd.read_csv(StringIO(df_csv))
[77]
0 s
# Visualiza los primeros registros para verificar que los datos se han cargado correctamente
print(df.head())
output
age gender height_cm weight_kg body fat_% diastolic systolic \
0 0 27.0 M 172.3 75.24 21.3 80.0 130.0
1 1 25.0 M 165.0 55.80 15.7 77.0 126.0
2 2 31.0 M 179.6 78.00 20.1 92.0 152.0
3 3 32.0 M 174.5 71.10 18.4 76.0 147.0
4 4 28.0 M 173.8 67.70 17.1 70.0 127.0
gripForce sit and bend forward_cm \
0 54.9 18.4
1 36.4 16.3
2 44.8 12.0
3 41.4 15.2
4 43.5 27.1
sit-ups counts broad jump_cm class
0 6... ... NaN NaN
1 53... ... NaN NaN
2 49... ... NaN NaN
3 53... ... NaN NaN
4 45... ... NaN NaN
[71]
0 s
print(df.columns)
output
Index([' age', 'gender', 'height_cm', 'weight_kg', 'body fat_%', 'diastolic',
'systolic', 'gripForce', 'sit and bend forward_cm', 'sit-ups counts',
'broad jump_cm', 'class'],
dtype='object')
[72]
altura = df['height_cm']
peso = df['weight_kg']
[73]
0 s
print(peso)
output
0 75.24
1 55.80
2 78.00
3 71.10
4 67.70
5 55.40
6 63.70
7 77.20
8 67.50
9 84.60
10 65.40
11 49.00
12 53.90
13 67.90
14 84.40
15 63.10
16 66.60
17 71.50
18 70.60
19 47.20
20 63.36
21 62.70
22 67.30
23 63.30
24 59.40
25 70.70
26 53.50
27 84.50
28 81.30
29 57.10
30 70.70
31 77.20
32 51.54
33 79.50
34 52.00
35 88.60
36 66.40
37 79.50
38 84.50
39 79.70
40 61.00
41 84.90
42 69.80
43 60.50
44 57.70
45 73.10
46 76.82
47 66.10
48 82.10
49 64.00
50 75.40
51 65.90
52 51.70
53 69.30
54 51.30
55 56.90
56 66.20
57 46.40
58 103.10
59 80.00
60 78.80
61 83.60
62 50.80
63 58.90
64 63.70
65 75.50
66 77.60
67 55.70
68 62.40
69 75.00
70 78.00
71 62.70
72 80.50
73 66.50
74 70.60
75 78.46
76 75.20
77 53.60
78 74.30
79 62.70
80 64.20
81 60.50
82 54.10
83 50.60
84 68.70
85 66.20
86 66.20
87 51.00
88 45.50
89 79.00
90 56.30
91 78.40
92 65.10
93 71.70
94 86.40
95 65.70
96 57.20
97 72.00
98 70.90
99 52.20
Name: weight_kg, dtype: float64
[74]
0 s
# Selecciona las columnas 'height_cm' y 'weight_kg'
nuevo_df = df[['height_cm', 'weight_kg']]
# Imprime el nuevo DataFrame
print(nuevo_df)
output
height_cm weight_kg
0 172.3 75.24
1 165.0 55.80
2 179.6 78.00
3 174.5 71.10
4 173.8 67.70
5 165.4 55.40
6 164.5 63.70
7 174.9 77.20
8 166.8 67.50
9 185.0 84.60
10 169.2 65.40
11 153.0 49.00
12 156.0 53.90
13 175.7 67.90
14 181.0 84.40
15 159.0 63.10
16 164.2 66.60
17 179.9 71.50
18 169.2 70.60
19 162.7 47.20
20 161.7 63.36
21 155.9 62.70
22 166.7 67.30
23 170.0 63.30
24 164.1 59.40
25 169.0 70.70
26 158.3 53.50
27 175.8 84.50
28 176.0 81.30
29 159.8 57.10
30 170.9 70.70
31 176.7 77.20
32 159.5 51.54
33 172.1 79.50
34 151.5 52.00
35 177.6 88.60
36 172.5 66.40
37 177.5 79.50
38 178.0 84.50
39 177.6 79.70
40 168.0 61.00
41 173.6 84.90
42 173.3 69.80
43 159.6 60.50
44 161.8 57.70
45 169.9 73.10
46 183.6 76.82
47 172.1 66.10
48 180.1 82.10
49 164.2 64.00
50 169.8 75.40
51 180.1 65.90
52 157.2 51.70
53 168.3 69.30
54 159.5 51.30
55 166.7 56.90
56 164.4 66.20
57 146.5 46.40
58 174.1 103.10
59 185.4 80.00
60 168.9 78.80
61 175.3 83.60
62 164.0 50.80
63 162.4 58.90
64 165.0 63.70
65 166.6 75.50
66 174.2 77.60
67 150.5 55.70
68 160.2 62.40
69 179.0 75.00
70 172.7 78.00
71 160.2 62.70
72 171.5 80.50
73 175.1 66.50
74 172.2 70.60
75 171.9 78.46
76 174.0 75.20
77 158.1 53.60
78 170.4 74.30
79 158.6 62.70
80 168.5 64.20
81 156.3 60.50
82 157.0 54.10
83 161.3 50.60
84 177.0 68.70
85 171.0 66.20
86 170.0 66.20
87 158.1 51.00
88 159.0 45.50
89 178.4 79.00
90 156.7 56.30
91 178.5 78.40
92 171.2 65.10
93 176.4 71.70
94 175.4 86.40
95 166.7 65.70
96 158.4 57.20
97 175.8 72.00
98 173.0 70.90
99 159.1 52.20
[75]
0 s
num_filas, num_columnas = df.shape
print(f"El DataFrame tiene {num_filas} filas y {num_columnas} columnas.")
output
El DataFrame tiene 100 filas y 12 columnas.
[76]
0 s
#numero de datos de la columna de pesos
nuevo_df['height_cm'].count()
output
100
[79]
0 s
# cuenta las ocurrencias de los pesos
tabla = df.groupby('height_cm').count()
tabla
output
[88]
0 s
# Lista de las columnas para las que deseas calcular tablas de frecuencia
columnas_de_interes = ['height_cm']
# Itera a través de las columnas de interés
for columna in columnas_de_interes:
tabla_frecuencia = df[columna].value_counts().reset_index()
tabla_frecuencia.columns = [columna, 'Frecuencia']
# Imprime la tabla de frecuencia para la columna actual
print(f"Tabla de Frecuencia para la columna '{columna}':")
print(tabla_frecuencia)
print("\n")
output
Tabla de Frecuencia para la columna 'height_cm':
height_cm Frecuencia
0 166.7 3
1 175.8 2
2 164.2 2
3 180.1 2
4 165.0 2
5 158.1 2
6 170.0 2
7 159.5 2
8 169.2 2
9 172.1 2
10 177.6 2
11 160.2 2
12 159.0 2
13 171.5 1
14 172.7 1
15 179.0 1
16 172.3 1
17 175.1 1
18 174.2 1
19 166.6 1
20 162.4 1
21 164.0 1
22 175.3 1
23 168.9 1
24 185.4 1
25 174.1 1
26 150.5 1
27 174.0 1
28 172.2 1
29 171.9 1
30 173.0 1
31 158.4 1
32 175.4 1
33 176.4 1
34 171.2 1
35 178.5 1
36 156.7 1
37 178.4 1
38 171.0 1
39 177.0 1
40 161.3 1
41 157.0 1
42 156.3 1
43 168.5 1
44 158.6 1
45 170.4 1
46 164.4 1
47 146.5 1
48 169.9 1
49 168.3 1
50 164.1 1
51 161.7 1
52 162.7 1
53 179.9 1
54 181.0 1
55 175.7 1
56 156.0 1
57 153.0 1
58 185.0 1
59 166.8 1
60 174.9 1
61 164.5 1
62 165.4 1
63 173.8 1
64 174.5 1
65 179.6 1
66 155.9 1
67 169.0 1
68 157.2 1
69 158.3 1
70 169.8 1
71 183.6 1
72 161.8 1
73 159.6 1
74 173.3 1
75 173.6 1
76 168.0 1
77 178.0 1
78 177.5 1
79 172.5 1
80 151.5 1
81 176.7 1
82 170.9 1
83 159.8 1
84 176.0 1
85 159.1 1
[87]
0 s
# Lista de las columnas para las que deseas calcular tablas de frecuencia
columnas_de_interes = ['weight_kg']
# Itera a través de las columnas de interés
for columna in columnas_de_interes:
tabla_frecuencia = df[columna].value_counts().reset_index()
tabla_frecuencia.columns = [columna, 'Frecuencia']
# Imprime la tabla de frecuencia para la columna actual
print(f"Tabla de Frecuencia para la columna '{columna}':")
print(tabla_frecuencia)
print("\n")
output
Tabla de Frecuencia para la columna 'weight_kg':
weight_kg Frecuencia
0 66.20 3
1 62.70 3
2 78.00 2
3 70.70 2
4 63.70 2
5 77.20 2
6 79.50 2
7 60.50 2
8 84.50 2
9 70.60 2
10 75.24 1
11 55.70 1
12 66.50 1
13 80.50 1
14 75.00 1
15 62.40 1
16 50.80 1
17 77.60 1
18 75.50 1
19 58.90 1
20 83.60 1
21 78.80 1
22 80.00 1
23 103.10 1
24 46.40 1
25 56.90 1
26 78.46 1
27 53.60 1
28 75.20 1
29 69.30 1
30 70.90 1
31 72.00 1
32 57.20 1
33 65.70 1
34 86.40 1
35 71.70 1
36 65.10 1
37 78.40 1
38 56.30 1
39 79.00 1
40 45.50 1
41 51.00 1
42 68.70 1
43 50.60 1
44 54.10 1
45 64.20 1
46 74.30 1
47 51.30 1
48 82.10 1
49 51.70 1
50 67.90 1
51 67.30 1
52 63.36 1
53 47.20 1
54 71.50 1
55 66.60 1
56 63.10 1
57 84.40 1
58 53.90 1
59 59.40 1
60 49.00 1
61 65.40 1
62 84.60 1
63 67.50 1
64 55.40 1
65 67.70 1
66 71.10 1
67 63.30 1
68 53.50 1
69 65.90 1
70 69.80 1
71 75.40 1
72 64.00 1
73 55.80 1
74 66.10 1
75 76.82 1
76 73.10 1
77 57.70 1
78 84.90 1
79 81.30 1
80 61.00 1
81 79.70 1
82 66.40 1
83 88.60 1
84 52.00 1
85 51.54 1
86 57.10 1
87 52.20 1
[90]
0 s
# muestra los pesos ordenados de menor a mayor
print(sorted(df['height_cm']))
output
[146.5, 150.5, 151.5, 153.0, 155.9, 156.0, 156.3, 156.7, 157.0, 157.2, 158.1, 158.1, 158.3, 158.4, 158.6, 159.0, 159.0, 159.1, 159.5, 159.5, 159.6, 159.8, 160.2, 160.2, 161.3, 161.7, 161.8, 162.4, 162.7, 164.0, 164.1, 164.2, 164.2, 164.4, 164.5, 165.0, 165.0, 165.4, 166.6, 166.7, 166.7, 166.7, 166.8, 168.0, 168.3, 168.5, 168.9, 169.0, 169.2, 169.2, 169.8, 169.9, 170.0, 170.0, 170.4, 170.9, 171.0, 171.2, 171.5, 171.9, 172.1, 172.1, 172.2, 172.3, 172.5, 172.7, 173.0, 173.3, 173.6, 173.8, 174.0, 174.1, 174.2, 174.5, 174.9, 175.1, 175.3, 175.4, 175.7, 175.8, 175.8, 176.0, 176.4, 176.7, 177.0, 177.5, 177.6, 177.6, 178.0, 178.4, 178.5, 179.0, 179.6, 179.9, 180.1, 180.1, 181.0, 183.6, 185.0, 185.4]
[91]
0 s
print(sorted(df['weight_kg']))
output
[45.5, 46.4, 47.2, 49.0, 50.6, 50.8, 51.0, 51.3, 51.54, 51.7, 52.0, 52.2, 53.5, 53.6, 53.9, 54.1, 55.4, 55.7, 55.8, 56.3, 56.9, 57.1, 57.2, 57.7, 58.9, 59.4, 60.5, 60.5, 61.0, 62.4, 62.7, 62.7, 62.7, 63.1, 63.3, 63.36, 63.7, 63.7, 64.0, 64.2, 65.1, 65.4, 65.7, 65.9, 66.1, 66.2, 66.2, 66.2, 66.4, 66.5, 66.6, 67.3, 67.5, 67.7, 67.9, 68.7, 69.3, 69.8, 70.6, 70.6, 70.7, 70.7, 70.9, 71.1, 71.5, 71.7, 72.0, 73.1, 74.3, 75.0, 75.2, 75.24, 75.4, 75.5, 76.82, 77.2, 77.2, 77.6, 78.0, 78.0, 78.4, 78.46, 78.8, 79.0, 79.5, 79.5, 79.7, 80.0, 80.5, 81.3, 82.1, 83.6, 84.4, 84.5, 84.5, 84.6, 84.9, 86.4, 88.6, 103.1]
[102]
0 s
## Intervalos de peso
# Datos de peso
peso_datos = [45.5, 46.4, 47.2, 49.0, 50.6, 50.8, 51.0, 51.3, 51.54, 51.7, 52.0, 52.2, 53.5, 53.6, 53.9, 54.1, 55.4, 55.7, 55.8, 56.3, 56.9, 57.1, 57.2, 57.7, 58.9, 59.4, 60.5, 60.5, 61.0, 62.4, 62.7, 62.7, 62.7, 63.1, 63.3, 63.36, 63.7, 63.7, 64.0, 64.2, 65.1, 65.4, 65.7, 65.9, 66.1, 66.2, 66.2, 66.2, 66.4, 66.5, 66.6, 67.3, 67.5, 67.7, 67.9, 68.7, 69.3, 69.8, 70.6, 70.6, 70.7, 70.7, 70.9, 71.1, 71.5, 71.7, 72.0, 73.1, 74.3, 75.0, 75.2, 75.24, 75.4, 75.5, 76.82, 77.2, 77.2, 77.6, 78.0, 78.0, 78.4, 78.46, 78.8, 79.0, 79.5, 79.5, 79.7, 80.0, 80.5, 81.3, 82.1, 83.6, 84.4, 84.5, 84.5, 84.6, 84.9, 86.4, 88.6, 103.1]
# Crea un DataFrame con los datos de peso
df = pd.DataFrame({'Peso': peso_datos})
# Define la cantidad de intervalos (en este caso, 5 intervalos)
num_intervalos = 5
# Utiliza la función cut para crear las categorías
categorias_peso = pd.cut(df['Peso'], bins=num_intervalos)
# Genera una tabla de frecuencia de las categorías
tabla_frecuencia = pd.crosstab(index=categorias_peso, columns="Frecuencia")
# Calcula la suma de las frecuencias
total = tabla_frecuencia['Frecuencia'].sum()
# Agrega una fila con el total
tabla_frecuencia = tabla_frecuencia.append({'Frecuencia': total}, ignore_index=True)
# Asigna un nombre a la fila del total
tabla_frecuencia = tabla_frecuencia.rename(index={num_intervalos: 'Total'})
# Imprime la tabla de frecuencia con el total
print(tabla_frecuencia)
output
Frecuencia
0 21
1 34
2 33
3 11
4 1
Total 100
<ipython-input-102-60d6335fb995>:21: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
tabla_frecuencia = tabla_frecuencia.append({'Frecuencia': total}, ignore_index=True)
[100]
0 s
# Datos de peso
peso_datos = [45.5, 46.4, 47.2, 49.0, 50.6, 50.8, 51.0, 51.3, 51.54, 51.7, 52.0, 52.2, 53.5, 53.6, 53.9, 54.1, 55.4, 55.7, 55.8, 56.3, 56.9, 57.1, 57.2, 57.7, 58.9, 59.4, 60.5, 60.5, 61.0, 62.4, 62.7, 62.7, 62.7, 63.1, 63.3, 63.36, 63.7, 63.7, 64.0, 64.2, 65.1, 65.4, 65.7, 65.9, 66.1, 66.2, 66.2, 66.2, 66.4, 66.5, 66.6, 67.3, 67.5, 67.7, 67.9, 68.7, 69.3, 69.8, 70.6, 70.6, 70.7, 70.7, 70.9, 71.1, 71.5, 71.7, 72.0, 73.1, 74.3, 75.0, 75.2, 75.24, 75.4, 75.5, 76.82, 77.2, 77.2, 77.6, 78.0, 78.0, 78.4, 78.46, 78.8, 79.0, 79.5, 79.5, 79.7, 80.0, 80.5, 81.3, 82.1, 83.6, 84.4, 84.5, 84.5, 84.6, 84.9, 86.4, 88.6, 103.1]
# Crea un DataFrame con los datos de peso
df = pd.DataFrame({'Peso': peso_datos})
# Define el intervalo de interés
intervalo_interes = [68.54, 80.06]
# Utiliza la función loc para seleccionar los pesos en ese intervalo
pesos_en_intervalo = df.loc[df['Peso'].between(intervalo_interes[0], intervalo_interes[1])]
# Imprime los pesos en el intervalo
print(pesos_en_intervalo)
output
Peso
55 68.70
56 69.30
57 69.80
58 70.60
59 70.60
60 70.70
61 70.70
62 70.90
63 71.10
64 71.50
65 71.70
66 72.00
67 73.10
68 74.30
69 75.00
70 75.20
71 75.24
72 75.40
73 75.50
74 76.82
75 77.20
76 77.20
77 77.60
78 78.00
79 78.00
80 78.40
81 78.46
82 78.80
83 79.00
84 79.50
85 79.50
86 79.70
87 80.00
[117]
0 s
# Calcula la suma de las frecuencias
total_frecuencia = tabla_frecuencia['Frecuencia'].sum()
# Agrega una fila con el total
tabla_frecuencia = tabla_frecuencia.append({'Intervalo': 'Total', 'Frecuencia': total_frecuencia}, ignore_index=True)
# Imprime la tabla de frecuencia con los intervalos y las frecuencias
print(tabla_frecuencia)
output
Intervalo Frecuencia
0 (146.461, 154.28] 4
1 (154.28, 162.06] 23
2 (162.06, 169.84] 24
3 (169.84, 177.62] 37
4 (177.62, 185.4] 12
5 Total 100
<ipython-input-117-3ee7f1ddf013>:25: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
tabla_frecuencia = tabla_frecuencia.append({'Intervalo': 'Total', 'Frecuencia': total_frecuencia}, ignore_index=True)
No hay comentarios:
Publicar un comentario