Skizze Wollknäuel

• Mathilda Musterfrau

• s-mmuster@haw…

• MatNr: 12 34 567

Problemstellungen

Beschrieben unter http://jbusse.de/dsci-ml_ws2022/Studienarbeit-SS-2023.html:

• abschätzen Körpergröße

• abschätzen Geschlecht

meine_Datei = "../data/MaennerFrauenKnaeuel.csv"

EDA Explorative Datenanalyse

import pandas as pd

df = pd.read_csv(meine_Datei, sep=";")

df.head()

	Unnamed: 0	age	height	spezies
0	0	0.0	60	b
1	1	5.5	88	b
2	2	13.8	0	b
3	3	4.1	91	b
4	4	13.8	165	b

df.describe()

	Unnamed: 0	age	height
count	1260.000000	1260.000000	1260.000000
mean	629.500000	25.519444	105.180952
std	363.874979	23.836270	70.534624
min	0.000000	0.000000	-6.000000
25%	314.750000	2.900000	30.000000
50%	629.500000	17.800000	127.000000
75%	944.250000	44.600000	169.000000
max	1259.000000	80.000000	208.000000

df.shape

(1260, 4)

df.columns

Index(['Unnamed: 0', 'age', 'height', 'spezies'], dtype='object')

df.spezies.unique()

array(['b', 'g', 'm', 'M', 'w', 'F', 'K'], dtype=object)

Problem 1: Abschätzen Körpergröße

y = df.pop("height")
y

0        60
1        88
2         0
3        91
4       165
       ... 
1255    104
1256    208
1257    112
1258      0
1259    140
Name: height, Length: 1260, dtype: int64

X = df
X

	Unnamed: 0	age	spezies
0	0	0.0	b
1	1	5.5	b
2	2	13.8	b
3	3	4.1	b
4	4	13.8	b
...	...	...	...
1255	1255	28.1	K
1256	1256	3.2	K
1257	1257	0.0	K
1258	1258	29.9	K
1259	1259	12.9	K

1260 rows × 3 columns

from sklearn.tree import DecisionTreeRegressor

# Define model. Specify a number for random_state to ensure same results each run
melbourne_model = DecisionTreeRegressor(random_state=1)

# Fit model
melbourne_model.fit(X, y)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In [11], line 7
      4 melbourne_model = DecisionTreeRegressor(random_state=1)
      6 # Fit model
----> 7 melbourne_model.fit(X, y)

File ~/miniconda3/lib/python3.9/site-packages/sklearn/tree/_classes.py:1342, in DecisionTreeRegressor.fit(self, X, y, sample_weight, check_input)
   1313 def fit(self, X, y, sample_weight=None, check_input=True):
   1314     """Build a decision tree regressor from the training set (X, y).
   1315 
   1316     Parameters
   (...)
   1339         Fitted estimator.
   1340     """
-> 1342     super().fit(
   1343         X,
   1344         y,
   1345         sample_weight=sample_weight,
   1346         check_input=check_input,
   1347     )
   1348     return self

File ~/miniconda3/lib/python3.9/site-packages/sklearn/tree/_classes.py:172, in BaseDecisionTree.fit(self, X, y, sample_weight, check_input)
    170 check_X_params = dict(dtype=DTYPE, accept_sparse="csc")
    171 check_y_params = dict(ensure_2d=False, dtype=None)
--> 172 X, y = self._validate_data(
    173     X, y, validate_separately=(check_X_params, check_y_params)
    174 )
    175 if issparse(X):
    176     X.sort_indices()

File ~/miniconda3/lib/python3.9/site-packages/sklearn/base.py:591, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
    589 if "estimator" not in check_X_params:
    590     check_X_params = {**default_check_params, **check_X_params}
--> 591 X = check_array(X, input_name="X", **check_X_params)
    592 if "estimator" not in check_y_params:
    593     check_y_params = {**default_check_params, **check_y_params}

File ~/miniconda3/lib/python3.9/site-packages/sklearn/utils/validation.py:856, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
    854         array = array.astype(dtype, casting="unsafe", copy=False)
    855     else:
--> 856         array = np.asarray(array, order=order, dtype=dtype)
    857 except ComplexWarning as complex_warning:
    858     raise ValueError(
    859         "Complex data not supported\n{}\n".format(array)
    860     ) from complex_warning

File ~/miniconda3/lib/python3.9/site-packages/pandas/core/generic.py:2069, in NDFrame.__array__(self, dtype)
   2068 def __array__(self, dtype: npt.DTypeLike | None = None) -> np.ndarray:
-> 2069     return np.asarray(self._values, dtype=dtype)

ValueError: could not convert string to float: 'b'

Aufgabe 2: Geschlecht abschätzen