Skizze Wollknäuel

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)
/tmp/ipykernel_13285/839580878.py in ?()
      3 # Define model. Specify a number for random_state to ensure same results each run
      4 melbourne_model = DecisionTreeRegressor(random_state=1)
      5 
      6 # Fit model
----> 7 melbourne_model.fit(X, y)

~/miniconda3/lib/python3.13/site-packages/sklearn/base.py in ?(estimator, *args, **kwargs)
   1361                 skip_parameter_validation=(
   1362                     prefer_skip_nested_validation or global_skip_validation
   1363                 )
   1364             ):
-> 1365                 return fit_method(estimator, *args, **kwargs)

~/miniconda3/lib/python3.13/site-packages/sklearn/tree/_classes.py in ?(self, X, y, sample_weight, check_input)
   1400         self : DecisionTreeRegressor
   1401             Fitted estimator.
   1402         """
   1403 
-> 1404         super()._fit(
   1405             X,
   1406             y,
   1407             sample_weight=sample_weight,

~/miniconda3/lib/python3.13/site-packages/sklearn/tree/_classes.py in ?(self, X, y, sample_weight, check_input, missing_values_in_feature_mask)
    248             check_X_params = dict(
    249                 dtype=DTYPE, accept_sparse="csc", ensure_all_finite=False
    250             )
    251             check_y_params = dict(ensure_2d=False, dtype=None)
--> 252             X, y = validate_data(
    253                 self, X, y, validate_separately=(check_X_params, check_y_params)
    254             )
    255 

~/miniconda3/lib/python3.13/site-packages/sklearn/utils/validation.py in ?(_estimator, X, y, reset, validate_separately, skip_check_array, **check_params)
   2962             # :(
   2963             check_X_params, check_y_params = validate_separately
   2964             if "estimator" not in check_X_params:
   2965                 check_X_params = {**default_check_params, **check_X_params}
-> 2966             X = check_array(X, input_name="X", **check_X_params)
   2967             if "estimator" not in check_y_params:
   2968                 check_y_params = {**default_check_params, **check_y_params}
   2969             y = check_array(y, input_name="y", **check_y_params)

~/miniconda3/lib/python3.13/site-packages/sklearn/utils/validation.py in ?(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_all_finite, ensure_non_negative, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
   1050                         )
   1051                     array = xp.astype(array, dtype, copy=False)
   1052                 else:
   1053                     array = _asarray_with_order(array, order=order, dtype=dtype, xp=xp)
-> 1054             except ComplexWarning as complex_warning:
   1055                 raise ValueError(
   1056                     "Complex data not supported\n{}\n".format(array)
   1057                 ) from complex_warning

~/miniconda3/lib/python3.13/site-packages/sklearn/utils/_array_api.py in ?(array, dtype, order, copy, xp, device)
    753         # Use NumPy API to support order
    754         if copy is True:
    755             array = numpy.array(array, order=order, dtype=dtype)
    756         else:
--> 757             array = numpy.asarray(array, order=order, dtype=dtype)
    758 
    759         # At this point array is a NumPy ndarray. We convert it to an array
    760         # container that is consistent with the input's namespace.

~/miniconda3/lib/python3.13/site-packages/pandas/core/generic.py in ?(self, dtype, copy)
   2164             )
   2165         values = self._values
   2166         if copy is None:
   2167             # Note: branch avoids `copy=None` for NumPy 1.x support
-> 2168             arr = np.asarray(values, dtype=dtype)
   2169         else:
   2170             arr = np.array(values, dtype=dtype, copy=copy)
   2171 

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

Aufgabe 2: Geschlecht abschätzen#

Contents