# Code attribution: Yiyin Shen, Tyler Caraza-Harter
# Imports
import sklearn
import sklearn.compose
import sklearn.pipeline
import sklearn.preprocessing
import sklearn.impute
import sklearn.linear_model
import sklearn.metrics
import pandas

# Read the Adult dataset
data = pandas.read_csv("adult.data", header = None, index_col = None, names = ["age", "workclass", "fnlwgt", "education", "education-num", "marital-status", "occupation", "relationship", "race", "sex", "capital-gain", "capital-loss", "hours-per-week", "native-country", "label"])
data.head(5)

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	label
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	0	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K

# Split features and labels
x = data.iloc[:, 0:14]
y = data.iloc[:, 14]
print(x.shape, y.shape)

(32561, 14) (32561,)

# Use column transformer on different columns
continuous = ["age", "education-num"]
discrete = ["workclass", "occupation"]
imputer_c = sklearn.impute.SimpleImputer(strategy = "median")
imputer_d = sklearn.impute.SimpleImputer(strategy = "constant", fill_value = "None")
transformer_c = sklearn.preprocessing.StandardScaler()
transformer_d = sklearn.preprocessing.OneHotEncoder()
steps_c = sklearn.pipeline.Pipeline(steps = [("ic", imputer_c), ("tc", transformer_c)])
steps_d = sklearn.pipeline.Pipeline(steps = [("id", imputer_d), ("td", transformer_d)])
pre = sklearn.compose.ColumnTransformer(transformers = [("c", steps_c, continuous), ("d", steps_d, discrete)])
model = sklearn.pipeline.Pipeline(steps = [("pre", pre), ("clf", sklearn.linear_model.LogisticRegression())])
model

Pipeline(steps=[('pre',
                 ColumnTransformer(transformers=[('c',
                                                  Pipeline(steps=[('ic',
                                                                   SimpleImputer(strategy='median')),
                                                                  ('tc',
                                                                   StandardScaler())]),
                                                  ['age', 'education-num']),
                                                 ('d',
                                                  Pipeline(steps=[('id',
                                                                   SimpleImputer(fill_value='None',
                                                                                 strategy='constant')),
                                                                  ('td',
                                                                   OneHotEncoder())]),
                                                  ['workclass',
                                                   'occupation'])])),
                ('clf', 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.

# Estimate the model and compute the confusion matrix on the training set
model.fit(x, y)
y_pred = model.predict(x)
sklearn.metrics.confusion_matrix(y, y_pred)

C:\Users\young\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\linear_model\_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

array([[23111,  1609],
       [ 5077,  2764]], dtype=int64)