ch04.py

# coding: utf-8


import sys
from python_environment_check import check_packages
import pandas as pd
from io import StringIO
from sklearn.impute import SimpleImputer
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
from sklearn.base import clone
from itertools import combinations
from sklearn.metrics import accuracy_score
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectFromModel

# # Machine Learning with PyTorch and Scikit-Learn  
# # -- Code Examples

# ## Package version checks

# Add folder to path in order to load from the check_packages.py script:



sys.path.insert(0, '..')


# Check recommended package versions:





d = {
    'numpy': '1.21.2',
    'matplotlib': '3.4.3',
    'sklearn': '1.0',
    'pandas': '1.3.2'
}
check_packages(d)


# # Chapter 4 - Building Good Training Datasets – Data Preprocessing


# ### Overview

# - [Dealing with missing data](#Dealing-with-missing-data)
#   - [Identifying missing values in tabular data](#Identifying-missing-values-in-tabular-data)
#   - [Eliminating training examples or features with missing values](#Eliminating-training-examples-or-features-with-missing-values)
#   - [Imputing missing values](#Imputing-missing-values)
#   - [Understanding the scikit-learn estimator API](#Understanding-the-scikit-learn-estimator-API)
# - [Handling categorical data](#Handling-categorical-data)
#   - [Nominal and ordinal features](#Nominal-and-ordinal-features)
#   - [Mapping ordinal features](#Mapping-ordinal-features)
#   - [Encoding class labels](#Encoding-class-labels)
#   - [Performing one-hot encoding on nominal features](#Performing-one-hot-encoding-on-nominal-features)
# - [Partitioning a dataset into a separate training and test set](#Partitioning-a-dataset-into-seperate-training-and-test-sets)
# - [Bringing features onto the same scale](#Bringing-features-onto-the-same-scale)
# - [Selecting meaningful features](#Selecting-meaningful-features)
#   - [L1 and L2 regularization as penalties against model complexity](#L1-and-L2-regularization-as-penalties-against-model-omplexity)
#   - [A geometric interpretation of L2 regularization](#A-geometric-interpretation-of-L2-regularization)
#   - [Sparse solutions with L1 regularization](#Sparse-solutions-with-L1-regularization)
#   - [Sequential feature selection algorithms](#Sequential-feature-selection-algorithms)
# - [Assessing feature importance with Random Forests](#Assessing-feature-importance-with-Random-Forests)
# - [Summary](#Summary)






# # Dealing with missing data

# ## Identifying missing values in tabular data




csv_data = '''A,B,C,D
1.0,2.0,3.0,4.0
5.0,6.0,,8.0
10.0,11.0,12.0,'''

# If you are using Python 2.7, you need
# to convert the string to unicode:

if (sys.version_info < (3, 0)):
    csv_data = unicode(csv_data)

df = pd.read_csv(StringIO(csv_data))
df




df.isnull().sum()




# access the underlying NumPy array
# via the `values` attribute
df.values



# ## Eliminating training examples or features with missing values



# remove rows that contain missing values

df.dropna(axis=0)




# remove columns that contain missing values

df.dropna(axis=1)




# remove columns that contain missing values

df.dropna(axis=1)




# only drop rows where all columns are NaN

df.dropna(how='all')  




# drop rows that have fewer than 3 real values 

df.dropna(thresh=4)




# only drop rows where NaN appear in specific columns (here: 'C')

df.dropna(subset=['C'])



# ## Imputing missing values



# again: our original array
df.values




# impute missing values via the column mean


imr = SimpleImputer(missing_values=np.nan, strategy='mean')
imr = imr.fit(df.values)
imputed_data = imr.transform(df.values)
imputed_data





df.fillna(df.mean())


# ## Understanding the scikit-learn estimator API










# # Handling categorical data

# ## Nominal and ordinal features




df = pd.DataFrame([['green', 'M', 10.1, 'class2'],
                   ['red', 'L', 13.5, 'class1'],
                   ['blue', 'XL', 15.3, 'class2']])

df.columns = ['color', 'size', 'price', 'classlabel']
df



# ## Mapping ordinal features



size_mapping = {'XL': 3,
                'L': 2,
                'M': 1}

df['size'] = df['size'].map(size_mapping)
df




inv_size_mapping = {v: k for k, v in size_mapping.items()}
df['size'].map(inv_size_mapping)



# ## Encoding class labels




# create a mapping dict
# to convert class labels from strings to integers
class_mapping = {label: idx for idx, label in enumerate(np.unique(df['classlabel']))}
class_mapping




# to convert class labels from strings to integers
df['classlabel'] = df['classlabel'].map(class_mapping)
df




# reverse the class label mapping
inv_class_mapping = {v: k for k, v in class_mapping.items()}
df['classlabel'] = df['classlabel'].map(inv_class_mapping)
df





# Label encoding with sklearn's LabelEncoder
class_le = LabelEncoder()
y = class_le.fit_transform(df['classlabel'].values)
y




# reverse mapping
class_le.inverse_transform(y)



# ## Performing one-hot encoding on nominal features



X = df[['color', 'size', 'price']].values
color_le = LabelEncoder()
X[:, 0] = color_le.fit_transform(X[:, 0])
X





X = df[['color', 'size', 'price']].values
color_ohe = OneHotEncoder()
color_ohe.fit_transform(X[:, 0].reshape(-1, 1)).toarray()





X = df[['color', 'size', 'price']].values
c_transf = ColumnTransformer([ ('onehot', OneHotEncoder(), [0]),
                               ('nothing', 'passthrough', [1, 2])])
c_transf.fit_transform(X).astype(float)




# one-hot encoding via pandas

pd.get_dummies(df[['price', 'color', 'size']])




# multicollinearity guard in get_dummies

pd.get_dummies(df[['price', 'color', 'size']], drop_first=True)




# multicollinearity guard for the OneHotEncoder

color_ohe = OneHotEncoder(categories='auto', drop='first')
c_transf = ColumnTransformer([ ('onehot', color_ohe, [0]),
                               ('nothing', 'passthrough', [1, 2])])
c_transf.fit_transform(X).astype(float)



# ## Optional: Encoding Ordinal Features

# If we are unsure about the numerical differences between the categories of ordinal features, or the difference between two ordinal values is not defined, we can also encode them using a threshold encoding with 0/1 values. For example, we can split the feature "size" with values M, L, and XL into two new features "x > M" and "x > L". Let's consider the original DataFrame:



df = pd.DataFrame([['green', 'M', 10.1, 'class2'],
                   ['red', 'L', 13.5, 'class1'],
                   ['blue', 'XL', 15.3, 'class2']])

df.columns = ['color', 'size', 'price', 'classlabel']
df


# We can use the `apply` method of pandas' DataFrames to write custom lambda expressions in order to encode these variables using the value-threshold approach:



df['x > M'] = df['size'].apply(lambda x: 1 if x in {'L', 'XL'} else 0)
df['x > L'] = df['size'].apply(lambda x: 1 if x == 'XL' else 0)

del df['size']
df



# # Partitioning a dataset into a seperate training and test set



df_wine = pd.read_csv('https://archive.ics.uci.edu/'
                      'ml/machine-learning-databases/wine/wine.data',
                      header=None)

# if the Wine dataset is temporarily unavailable from the
# UCI machine learning repository, un-comment the following line
# of code to load the dataset from a local path:

# df_wine = pd.read_csv('wine.data', header=None)


df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
                   'Alcalinity of ash', 'Magnesium', 'Total phenols',
                   'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
                   'Color intensity', 'Hue', 'OD280/OD315 of diluted wines',
                   'Proline']

print('Class labels', np.unique(df_wine['Class label']))
df_wine.head()





X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values

X_train, X_test, y_train, y_test =    train_test_split(X, y, 
                     test_size=0.3, 
                     random_state=0, 
                     stratify=y)



# # Bringing features onto the same scale




mms = MinMaxScaler()
X_train_norm = mms.fit_transform(X_train)
X_test_norm = mms.transform(X_test)





stdsc = StandardScaler()
X_train_std = stdsc.fit_transform(X_train)
X_test_std = stdsc.transform(X_test)


# A visual example:



ex = np.array([0, 1, 2, 3, 4, 5])

print('standardized:', (ex - ex.mean()) / ex.std())

# Please note that pandas uses ddof=1 (sample standard deviation) 
# by default, whereas NumPy's std method and the StandardScaler
# uses ddof=0 (population standard deviation)

# normalize
print('normalized:', (ex - ex.min()) / (ex.max() - ex.min()))



# # Selecting meaningful features

# ...

# ## L1 and L2 regularization as penalties against model complexity

# ## A geometric interpretation of L2 regularization









# ## Sparse solutions with L1-regularization





# For regularized models in scikit-learn that support L1 regularization, we can simply set the `penalty` parameter to `'l1'` to obtain a sparse solution:




LogisticRegression(penalty='l1')


# Applied to the standardized Wine data ...




lr = LogisticRegression(penalty='l1', C=1.0, solver='liblinear', multi_class='ovr')
# Note that C=1.0 is the default. You can increase
# or decrease it to make the regulariztion effect
# weaker or stronger, respectively.
lr.fit(X_train_std, y_train)
print('Training accuracy:', lr.score(X_train_std, y_train))
print('Test accuracy:', lr.score(X_test_std, y_test))




lr.intercept_




np.set_printoptions(8)




lr.coef_[lr.coef_!=0].shape




lr.coef_





fig = plt.figure()
ax = plt.subplot(111)
    
colors = ['blue', 'green', 'red', 'cyan', 
          'magenta', 'yellow', 'black', 
          'pink', 'lightgreen', 'lightblue', 
          'gray', 'indigo', 'orange']

weights, params = [], []
for c in np.arange(-4., 6.):
    lr = LogisticRegression(penalty='l1', C=10.**c, solver='liblinear', 
                            multi_class='ovr', random_state=0)
    lr.fit(X_train_std, y_train)
    weights.append(lr.coef_[1])
    params.append(10**c)

weights = np.array(weights)

for column, color in zip(range(weights.shape[1]), colors):
    plt.plot(params, weights[:, column],
             label=df_wine.columns[column + 1],
             color=color)
plt.axhline(0, color='black', linestyle='--', linewidth=3)
plt.xlim([10**(-5), 10**5])
plt.ylabel('Weight coefficient')
plt.xlabel('C (inverse regularization strength)')
plt.xscale('log')
plt.legend(loc='upper left')
ax.legend(loc='upper center', 
          bbox_to_anchor=(1.38, 1.03),
          ncol=1, fancybox=True)

#plt.savefig('figures/04_08.png', dpi=300, 
#            bbox_inches='tight', pad_inches=0.2)

plt.show()



# ## Sequential feature selection algorithms





class SBS:
    def __init__(self, estimator, k_features, scoring=accuracy_score,
                 test_size=0.25, random_state=1):
        self.scoring = scoring
        self.estimator = clone(estimator)
        self.k_features = k_features
        self.test_size = test_size
        self.random_state = random_state

    def fit(self, X, y):
        
        X_train, X_test, y_train, y_test =             train_test_split(X, y, test_size=self.test_size,
                             random_state=self.random_state)

        dim = X_train.shape[1]
        self.indices_ = tuple(range(dim))
        self.subsets_ = [self.indices_]
        score = self._calc_score(X_train, y_train, 
                                 X_test, y_test, self.indices_)
        self.scores_ = [score]

        while dim > self.k_features:
            scores = []
            subsets = []

            for p in combinations(self.indices_, r=dim - 1):
                score = self._calc_score(X_train, y_train, 
                                         X_test, y_test, p)
                scores.append(score)
                subsets.append(p)

            best = np.argmax(scores)
            self.indices_ = subsets[best]
            self.subsets_.append(self.indices_)
            dim -= 1

            self.scores_.append(scores[best])
        self.k_score_ = self.scores_[-1]

        return self

    def transform(self, X):
        return X[:, self.indices_]

    def _calc_score(self, X_train, y_train, X_test, y_test, indices):
        self.estimator.fit(X_train[:, indices], y_train)
        y_pred = self.estimator.predict(X_test[:, indices])
        score = self.scoring(y_test, y_pred)
        return score





knn = KNeighborsClassifier(n_neighbors=5)

# selecting features
sbs = SBS(knn, k_features=1)
sbs.fit(X_train_std, y_train)

# plotting performance of feature subsets
k_feat = [len(k) for k in sbs.subsets_]

plt.plot(k_feat, sbs.scores_, marker='o')
plt.ylim([0.7, 1.02])
plt.ylabel('Accuracy')
plt.xlabel('Number of features')
plt.grid()
plt.tight_layout()
# plt.savefig('figures/04_09.png', dpi=300)
plt.show()




k3 = list(sbs.subsets_[10])
print(df_wine.columns[1:][k3])




knn.fit(X_train_std, y_train)
print('Training accuracy:', knn.score(X_train_std, y_train))
print('Test accuracy:', knn.score(X_test_std, y_test))




knn.fit(X_train_std[:, k3], y_train)
print('Training accuracy:', knn.score(X_train_std[:, k3], y_train))
print('Test accuracy:', knn.score(X_test_std[:, k3], y_test))



# # Assessing feature importance with Random Forests




feat_labels = df_wine.columns[1:]

forest = RandomForestClassifier(n_estimators=500,
                                random_state=1)

forest.fit(X_train, y_train)
importances = forest.feature_importances_

indices = np.argsort(importances)[::-1]

for f in range(X_train.shape[1]):
    print("%2d) %-*s %f" % (f + 1, 30, 
                            feat_labels[indices[f]], 
                            importances[indices[f]]))

plt.title('Feature importance')
plt.bar(range(X_train.shape[1]), 
        importances[indices],
        align='center')

plt.xticks(range(X_train.shape[1]), 
           feat_labels[indices], rotation=90)
plt.xlim([-1, X_train.shape[1]])
plt.tight_layout()
# plt.savefig('figures/04_10.png', dpi=300)
plt.show()





sfm = SelectFromModel(forest, threshold=0.1, prefit=True)
X_selected = sfm.transform(X_train)
print('Number of features that meet this threshold criterion:', 
      X_selected.shape[1])


# Now, let's print the 3 features that met the threshold criterion for feature selection that we set earlier (note that this code snippet does not appear in the actual book but was added to this notebook later for illustrative purposes):



for f in range(X_selected.shape[1]):
    print("%2d) %-*s %f" % (f + 1, 30, 
                            feat_labels[indices[f]], 
                            importances[indices[f]]))



# # Summary

# ...

# ---
# 
# Readers may ignore the next cell.