Schuhgröße – Geschlecht

import pandas as pd

datei = "synthetische_daten_3bis40_mit_BMI_Kategorien.csv"

df = pd.read_csv(datei, index_col="ID")

df.head()

	Alter_Jahre	Geschlecht	Körpergröße_cm	Gewicht_kg	BMI	BMI_Kategorie	Schuhgröße_EU
ID
1	20	w	165.6	58.1	21.2	Normalgewicht	40
2	4	m	101.1	11.8	11.5	Untergewichtig	25
3	12	m	147.5	35.7	16.4	Normalgewicht	35
4	19	m	177.4	68.0	21.6	Normalgewicht	42
5	6	m	122.0	22.8	15.3	Normalgewicht	30

from sklearn.model_selection import train_test_split

y = df["Geschlecht"]

type(y)

pandas.core.series.Series

df.columns

Index(['Alter_Jahre', 'Geschlecht', 'Körpergröße_cm', 'Gewicht_kg', 'BMI',
       'BMI_Kategorie', 'Schuhgröße_EU'],
      dtype='object')

X = df.drop(["Geschlecht" , "BMI_Kategorie" ] , axis=1)

X

	Alter_Jahre	Körpergröße_cm	Gewicht_kg	BMI	Schuhgröße_EU
ID
1	20	165.6	58.1	21.2	40
2	4	101.1	11.8	11.5	25
3	12	147.5	35.7	16.4	35
4	19	177.4	68.0	21.6	42
5	6	122.0	22.8	15.3	30
...	...	...	...	...	...
1496	22	189.3	88.9	24.8	45
1497	35	166.1	62.6	22.7	40
1498	28	165.2	65.5	24.0	39
1499	39	172.3	68.0	22.9	41
1500	32	180.6	82.8	25.4	43

1500 rows × 5 columns

X.describe()

	Alter_Jahre	Körpergröße_cm	Gewicht_kg	BMI	Schuhgröße_EU
count	1500.000000	1500.000000	1500.000000	1500.000000	1500.000000
mean	18.564667	154.977533	53.709733	20.777133	37.106667
std	10.557531	25.751946	23.149581	4.299159	5.803138
min	3.000000	81.300000	7.000000	9.500000	21.000000
25%	10.000000	138.500000	31.975000	17.400000	33.000000
50%	17.000000	164.700000	58.900000	21.100000	39.000000
75%	27.000000	173.800000	71.150000	23.800000	41.000000
max	40.000000	194.400000	110.300000	33.500000	46.000000

from sklearn.model_selection import train_test_split

train_X, val_X, train_y, val_y = train_test_split(X, y, random_state = 0)

train_X.shape

(1125, 5)

val_X.shape

(375, 5)

from sklearn.linear_model import LogisticRegression

reg = LogisticRegression() # regression in weiterem Sinn: auch Klassen

reg.fit(train_X, train_y)

LogisticRegression()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

val_X

	Alter_Jahre	Körpergröße_cm	Gewicht_kg	BMI	Schuhgröße_EU
ID
472	15	170.9	65.1	22.3	41
10	8	125.7	21.0	13.3	31
1500	32	180.6	82.8	25.4	43
55	3	102.8	16.1	15.2	25
1412	37	165.5	63.5	23.2	39
...	...	...	...	...	...
76	4	105.5	20.3	18.2	26
482	6	107.9	18.9	16.2	27
1351	22	179.9	85.1	26.3	43
749	7	122.4	20.7	13.8	30
1363	22	187.7	88.4	25.1	44

375 rows × 5 columns

predict_y = reg.predict( val_X ) 

len(predict_y), len(val_y)

(375, 375)

predict_y[:10]

array(['m', 'm', 'm', 'm', 'w', 'm', 'm', 'w', 'm', 'w'], dtype=object)

list(val_y[:10])

['m', 'm', 'm', 'w', 'w', 'm', 'm', 'w', 'm', 'w']

"""
differenz = []
for i in range(0,10):
    v = list(val_y)[i]
    p = list(predict_y)[i]
    
    # print( f"val: {v}, predict: {p}")
    differenz.append( abs(v-p) )
differenz
MAE = sum( differenz ) / len( differenz )
MAE
"""

'\ndifferenz = []\nfor i in range(0,10):\n    v = list(val_y)[i]\n    p = list(predict_y)[i]\n\n    # print( f"val: {v}, predict: {p}")\n    differenz.append( abs(v-p) )\ndifferenz\nMAE = sum( differenz ) / len( differenz )\nMAE\n'

cm = { "m" : { "m": 0, "w": 0 },
       "w":  { "m": 0, "w": 0 }}

for i in range(len( val_y )):

    v = list(val_y)[i]
    p = list(predict_y)[i]
    
    #print(v ,  p )
    cm[ v ][ p ] += 1
cm

{'m': {'m': 136, 'w': 70}, 'w': {'m': 48, 'w': 121}}

Diskussion siehe https://en.wikipedia.org/wiki/Confusion_matrix