import math
-import numpy as np
-import matplotlib.pylab as plt
-%matplotlib inline
-
-# importing all the required libraries
-
-from math import exp
-import numpy as np
-import pandas as pd
-import seaborn as sns
-import sklearn
-from sklearn.linear_model import LogisticRegression
-from sklearn.tree import DecisionTreeClassifier
-from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
-from sklearn.svm import SVC, LinearSVC
-from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
-from matplotlib.colors import Normalize
-import matplotlib.pyplot as plt
-%matplotlib inline
-
-from sklearn.metrics import roc_auc_score
-from sklearn.metrics import roc_curve
-

!pip install ucimlrepo
-

Requirement already satisfied: ucimlrepo in /opt/conda/lib/python3.7/site-packages (0.0.7)
-Requirement already satisfied: pandas>=1.0.0 in /opt/conda/lib/python3.7/site-packages (from ucimlrepo) (1.0.3)
-Requirement already satisfied: certifi>=2020.12.5 in /opt/conda/lib/python3.7/site-packages (from ucimlrepo) (2025.1.31)
-Requirement already satisfied: python-dateutil>=2.6.1 in /opt/conda/lib/python3.7/site-packages (from pandas>=1.0.0->ucimlrepo) (2.8.1)
-Requirement already satisfied: pytz>=2017.2 in /opt/conda/lib/python3.7/site-packages (from pandas>=1.0.0->ucimlrepo) (2020.1)
-Requirement already satisfied: numpy>=1.13.3 in /opt/conda/lib/python3.7/site-packages (from pandas>=1.0.0->ucimlrepo) (1.18.4)
-Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.7/site-packages (from python-dateutil>=2.6.1->pandas>=1.0.0->ucimlrepo) (1.14.0)
-
-[notice] A new release of pip is available: 23.3.2 -> 24.0
-[notice] To update, run: pip install --upgrade pip
-

from ucimlrepo import fetch_ucirepo
-
-# fetch dataset
-spambase = fetch_ucirepo(id=94)
-  
-# data (as pandas dataframes)
-X = spambase.data.features
-y = spambase.data.targets
-  
-# variable information
-print(spambase.variables)
-
-# metadata
-spambase.metadata
-

                          name     role        type demographic  \
-0               word_freq_make  Feature  Continuous        None   
-1            word_freq_address  Feature  Continuous        None   
-2                word_freq_all  Feature  Continuous        None   
-3                 word_freq_3d  Feature  Continuous        None   
-4                word_freq_our  Feature  Continuous        None   
-5               word_freq_over  Feature  Continuous        None   
-6             word_freq_remove  Feature  Continuous        None   
-7           word_freq_internet  Feature  Continuous        None   
-8              word_freq_order  Feature  Continuous        None   
-9               word_freq_mail  Feature  Continuous        None   
-10           word_freq_receive  Feature  Continuous        None   
-11              word_freq_will  Feature  Continuous        None   
-12            word_freq_people  Feature  Continuous        None   
-13            word_freq_report  Feature  Continuous        None   
-14         word_freq_addresses  Feature  Continuous        None   
-15              word_freq_free  Feature  Continuous        None   
-16          word_freq_business  Feature  Continuous        None   
-17             word_freq_email  Feature  Continuous        None   
-18               word_freq_you  Feature  Continuous        None   
-19            word_freq_credit  Feature  Continuous        None   
-20              word_freq_your  Feature  Continuous        None   
-21              word_freq_font  Feature  Continuous        None   
-22               word_freq_000  Feature  Continuous        None   
-23             word_freq_money  Feature  Continuous        None   
-24                word_freq_hp  Feature  Continuous        None   
-25               word_freq_hpl  Feature  Continuous        None   
-26            word_freq_george  Feature  Continuous        None   
-27               word_freq_650  Feature  Continuous        None   
-28               word_freq_lab  Feature  Continuous        None   
-29              word_freq_labs  Feature  Continuous        None   
-30            word_freq_telnet  Feature  Continuous        None   
-31               word_freq_857  Feature  Continuous        None   
-32              word_freq_data  Feature  Continuous        None   
-33               word_freq_415  Feature  Continuous        None   
-34                word_freq_85  Feature  Continuous        None   
-35        word_freq_technology  Feature  Continuous        None   
-36              word_freq_1999  Feature  Continuous        None   
-37             word_freq_parts  Feature  Continuous        None   
-38                word_freq_pm  Feature  Continuous        None   
-39            word_freq_direct  Feature  Continuous        None   
-40                word_freq_cs  Feature  Continuous        None   
-41           word_freq_meeting  Feature  Continuous        None   
-42          word_freq_original  Feature  Continuous        None   
-43           word_freq_project  Feature  Continuous        None   
-44                word_freq_re  Feature  Continuous        None   
-45               word_freq_edu  Feature  Continuous        None   
-46             word_freq_table  Feature  Continuous        None   
-47        word_freq_conference  Feature  Continuous        None   
-48                 char_freq_;  Feature  Continuous        None   
-49                 char_freq_(  Feature  Continuous        None   
-50                 char_freq_[  Feature  Continuous        None   
-51                 char_freq_!  Feature  Continuous        None   
-52                 char_freq_$  Feature  Continuous        None   
-53                 char_freq_#  Feature  Continuous        None   
-54  capital_run_length_average  Feature  Continuous        None   
-55  capital_run_length_longest  Feature  Continuous        None   
-56    capital_run_length_total  Feature  Continuous        None   
-57                       Class   Target      Binary        None   
-
-                 description units missing_values  
-0                       None  None             no  
-1                       None  None             no  
-2                       None  None             no  
-3                       None  None             no  
-4                       None  None             no  
-5                       None  None             no  
-6                       None  None             no  
-7                       None  None             no  
-8                       None  None             no  
-9                       None  None             no  
-10                      None  None             no  
-11                      None  None             no  
-12                      None  None             no  
-13                      None  None             no  
-14                      None  None             no  
-15                      None  None             no  
-16                      None  None             no  
-17                      None  None             no  
-18                      None  None             no  
-19                      None  None             no  
-20                      None  None             no  
-21                      None  None             no  
-22                      None  None             no  
-23                      None  None             no  
-24                      None  None             no  
-25                      None  None             no  
-26                      None  None             no  
-27                      None  None             no  
-28                      None  None             no  
-29                      None  None             no  
-30                      None  None             no  
-31                      None  None             no  
-32                      None  None             no  
-33                      None  None             no  
-34                      None  None             no  
-35                      None  None             no  
-36                      None  None             no  
-37                      None  None             no  
-38                      None  None             no  
-39                      None  None             no  
-40                      None  None             no  
-41                      None  None             no  
-42                      None  None             no  
-43                      None  None             no  
-44                      None  None             no  
-45                      None  None             no  
-46                      None  None             no  
-47                      None  None             no  
-48                      None  None             no  
-49                      None  None             no  
-50                      None  None             no  
-51                      None  None             no  
-52                      None  None             no  
-53                      None  None             no  
-54                      None  None             no  
-55                      None  None             no  
-56                      None  None             no  
-57  spam (1) or not spam (0)  None             no  
-

{'uci_id': 94,
- 'name': 'Spambase',
- 'repository_url': 'https://archive.ics.uci.edu/dataset/94/spambase',
- 'data_url': 'https://archive.ics.uci.edu/static/public/94/data.csv',
- 'abstract': 'Classifying Email as Spam or Non-Spam',
- 'area': 'Computer Science',
- 'tasks': ['Classification'],
- 'characteristics': ['Multivariate'],
- 'num_instances': 4601,
- 'num_features': 57,
- 'feature_types': ['Integer', 'Real'],
- 'demographics': [],
- 'target_col': ['Class'],
- 'index_col': None,
- 'has_missing_values': 'no',
- 'missing_values_symbol': None,
- 'year_of_dataset_creation': 1999,
- 'last_updated': 'Mon Aug 28 2023',
- 'dataset_doi': '10.24432/C53G6X',
- 'creators': ['Mark Hopkins',
-  'Erik Reeber',
-  'George Forman',
-  'Jaap Suermondt'],
- 'intro_paper': None,
- 'additional_info': {'summary': 'The "spam" concept is diverse: advertisements for products/web sites, make money fast schemes, chain letters, pornography...\n\nThe classification task for this dataset is to determine whether a given email is spam or not.\n\t\nOur collection of spam e-mails came from our postmaster and individuals who had filed spam.  Our collection of non-spam e-mails came from filed work and personal e-mails, and hence the word \'george\' and the area code \'650\' are indicators of non-spam.  These are useful when constructing a personalized spam filter.  One would either have to blind such non-spam indicators or get a very wide collection of non-spam to generate a general purpose spam filter.\n\nFor background on spam: Cranor, Lorrie F., LaMacchia, Brian A.  Spam!, Communications of the ACM, 41(8):74-83, 1998.\n\nTypical performance is around ~7% misclassification error. False positives (marking good mail as spam) are very undesirable.If we insist on zero false positives in the training/testing set, 20-25% of the spam passed through the filter. See also Hewlett-Packard Internal-only Technical Report. External version forthcoming. ',
-  'purpose': None,
-  'funded_by': None,
-  'instances_represent': 'Emails',
-  'recommended_data_splits': None,
-  'sensitive_data': None,
-  'preprocessing_description': None,
-  'variable_info': 'The last column of \'spambase.data\' denotes whether the e-mail was considered spam (1) or not (0), i.e. unsolicited commercial e-mail.  Most of the attributes indicate whether a particular word or character was frequently occuring in the e-mail.  The run-length attributes (55-57) measure the length of sequences of consecutive capital letters.  For the statistical measures of each attribute, see the end of this file.  Here are the definitions of the attributes:\r\n\r\n48 continuous real [0,100] attributes of type word_freq_WORD \r\n= percentage of words in the e-mail that match WORD, i.e. 100 * (number of times the WORD appears in the e-mail) / total number of words in e-mail.  A "word" in this case is any string of alphanumeric characters bounded by non-alphanumeric characters or end-of-string.\r\n\r\n6 continuous real [0,100] attributes of type char_freq_CHAR] \r\n= percentage of characters in the e-mail that match CHAR, i.e. 100 * (number of CHAR occurences) / total characters in e-mail\r\n\r\n1 continuous real [1,...] attribute of type capital_run_length_average \r\n= average length of uninterrupted sequences of capital letters\r\n\r\n1 continuous integer [1,...] attribute of type capital_run_length_longest \r\n= length of longest uninterrupted sequence of capital letters\r\n\r\n1 continuous integer [1,...] attribute of type capital_run_length_total \r\n= sum of length of uninterrupted sequences of capital letters \r\n= total number of capital letters in the e-mail\r\n\r\n1 nominal {0,1} class attribute of type spam\r\n= denotes whether the e-mail was considered spam (1) or not (0), i.e. unsolicited commercial e-mail.  \r\n',
-  'citation': None}}

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=10, test_size=.1)
-

# Adapted from Module 6, used by plotSearchGrid
-class MidpointNormalize(Normalize):
-
-    def __init__(self, vmin=None, vmax=None, midpoint=None, clip=False):
-        self.midpoint = midpoint
-        Normalize.__init__(self, vmin, vmax, clip)
-
-    def __call__(self, value, clip=None):
-        x, y = [self.vmin, self.midpoint, self.vmax], [0, 0.5, 1]
-        return np.ma.masked_array(np.interp(value, x, y))
-
-# Adapted from Module 6
-def plotSearchGrid(grid, var1, var2):
-    scores = [x for x in grid.cv_results_["mean_test_score"]]
-    scores = np.array(scores).reshape(len(grid.param_grid[var1]), len(grid.param_grid[var2]))
-    #plt.figure(figsize=(10, 8))
-    plt.subplots_adjust(left=.2, right=0.95, bottom=0.15, top=0.95)
-    plt.imshow(scores, interpolation='nearest', cmap=plt.cm.hot,
-               norm=MidpointNormalize(vmin=0.2, midpoint=0.92))
-    plt.xlabel(var2)
-    plt.ylabel(var1)
-    plt.colorbar()
-    plt.xticks(np.arange(len(grid.param_grid[var2])), grid.param_grid[var2], rotation=45)
-    plt.yticks(np.arange(len(grid.param_grid[var1])), grid.param_grid[var1])
-    plt.title('Validation accuracy')
-    plt.show()
-
-def calculate_precision(y_true, y_pred, pos_label_value=1.0):
-    '''
-    This function accepts the labels and the predictions, then
-    calculates precision for a binary classifier.
-    
-    Args
-        y_true: np.ndarray
-        y_pred: np.ndarray
-        
-        pos_label_value: (float) the number which represents the postiive
-        label in the y_true and y_pred arrays. Other numbers will be taken
-        to be the non-positive class for the binary classifier.
-    
-    Returns precision as a floating point number between 0.0 and 1.0
-    '''
-    TP = np.sum((y_true == pos_label_value) * (y_pred == pos_label_value))
-    P_data = np.sum(y_pred == pos_label_value)
-    return TP/P_data
-
-def calculate_recall(y_true, y_pred, pos_label_value=1.0):
-    '''
-    This function accepts the labels and the predictions, then
-    calculates recall for a binary classifier.
-    
-    Args
-        y_true: np.ndarray
-        y_pred: np.ndarray
-        
-        pos_label_value: (float) the number which represents the postiive
-        label in the y_true and y_pred arrays. Other numbers will be taken
-        to be the non-positive class for the binary classifier.
-    
-    Returns precision as a floating point number between 0.0 and 1.0
-    '''
-    TP = np.sum((y_true == pos_label_value) * (y_pred == pos_label_value))
-    P_data = np.sum(y_true == pos_label_value)
-    return TP/P_data
-

sns.heatmap(X.corr(), -1, 1, "coolwarm", 0, annot=True, ax=plt.subplots(figsize=(30,30))[1])
-

<matplotlib.axes._subplots.AxesSubplot at 0x7535ac4d7bd0>

sns.pairplot(X[["word_freq_hp", "word_freq_hpl", "word_freq_650", "word_freq_lab", "word_freq_labs", "word_freq_telnet", "word_freq_857", "word_freq_415", "word_freq_85", "word_freq_technology", "word_freq_direct"]], diag_kind="kde")
-

<seaborn.axisgrid.PairGrid at 0x75353521aa90>

sns.pairplot(X[["capital_run_length_average", "capital_run_length_longest", "capital_run_length_total"]], diag_kind="kde")
-

<seaborn.axisgrid.PairGrid at 0x75352d98bc90>

LogRegGrid = GridSearchCV(
-    LogisticRegression(solver="liblinear"),
-    {
-        "penalty": ("l1", "l2"),
-        "C": np.logspace(-5, 5, base=2, num=11)
-    }
-).fit(X_train, y_train)
-

plotSearchGrid(LogRegGrid, "C", "penalty")
-print("Best Logistic Regression parameters:", LogRegGrid.best_params_)
-print("Best Logistic Regression score:", LogRegGrid.best_score_)
-LogRegBest = LogRegGrid.best_estimator_
-

Best Logistic Regression parameters: {'C': 8.0, 'penalty': 'l1'}
-Best Logistic Regression score: 0.9231884057971016
-

for feature, coef in zip(X.columns.tolist(), LogRegBest.coef_[0]):
-    print(feature, ":", coef)
-

word_freq_make : -0.3352771610625865
-word_freq_address : -0.144134104466229
-word_freq_all : 0.112018672406649
-word_freq_3d : 2.076387357353494
-word_freq_our : 0.554593550485832
-word_freq_over : 1.2904401963364194
-word_freq_remove : 2.5267285725399806
-word_freq_internet : 0.5172196645160981
-word_freq_order : 0.627473532037221
-word_freq_mail : 0.17249868699823487
-word_freq_receive : -0.25581126978924495
-word_freq_will : -0.14234046357326724
-word_freq_people : -0.11854115705721327
-word_freq_report : 0.17412149671014215
-word_freq_addresses : 1.0500388675253347
-word_freq_free : 0.9634466906627731
-word_freq_business : 0.9305392973545669
-word_freq_email : 0.10133392987631257
-word_freq_you : 0.08488243536713497
-word_freq_credit : 1.3819517056872157
-word_freq_your : 0.2654681374949797
-word_freq_font : 0.21749820028292105
-word_freq_000 : 2.0810250283128378
-word_freq_money : 0.36561247488532317
-word_freq_hp : -1.7902775548167147
-word_freq_hpl : -1.2336732801585475
-word_freq_george : -10.880824805770052
-word_freq_650 : 0.44226034330510694
-word_freq_lab : -2.2885745842672742
-word_freq_labs : -0.2654647593774336
-word_freq_telnet : -0.16163430120735922
-word_freq_857 : 0.0
-word_freq_data : -0.785684361230612
-word_freq_415 : 0.45936893654380306
-word_freq_85 : -1.9259154363336377
-word_freq_technology : 0.8586013549791187
-word_freq_1999 : 0.09105557504327932
-word_freq_parts : -0.5351601870000458
-word_freq_pm : -0.7897860751763727
-word_freq_direct : -0.3114823079515479
-word_freq_cs : -16.272347427710518
-word_freq_meeting : -2.513144116975214
-word_freq_original : -1.1180888218223113
-word_freq_project : -1.6215101779132928
-word_freq_re : -0.8091323320430137
-word_freq_edu : -1.307624281598115
-word_freq_table : -1.3921522502944936
-word_freq_conference : -3.6846542873407873
-char_freq_; : -1.233208442411895
-char_freq_( : -0.13236694620475534
-char_freq_[ : -0.545299178734433
-char_freq_! : 0.3144554745969651
-char_freq_$ : 4.90464860192831
-char_freq_# : 1.85535122747682
-capital_run_length_average : 0.014264456456158873
-capital_run_length_longest : 0.007832612484971016
-capital_run_length_total : 0.0008400454072136723
-

RFGrid = GridSearchCV(
-    RandomForestClassifier(max_samples=.7),
-    {
-        "max_depth": range(10, 20, 3),
-        "n_estimators": range(100, 1100, 300)
-    }
-).fit(X_train, y_train)
-

plotSearchGrid(RFGrid, "max_depth", "n_estimators")
-print("Best Random Forest parameters:", RFGrid.best_params_)
-print("Best Random Forest score:", RFGrid.best_score_)
-RFBest = RFGrid.best_estimator_
-

Best Random Forest parameters: {'max_depth': 19, 'n_estimators': 700}
-Best Random Forest score: 0.9487922705314009
-

ABGrid = GridSearchCV(
-    AdaBoostClassifier(),
-    {
-        "learning_rate": np.logspace(-4, -1, base=2, num=4),
-        "n_estimators": range(100, 1100, 300)
-    }
-).fit(X_train, y_train)
-

plotSearchGrid(ABGrid, "learning_rate", "n_estimators")
-print("Best AdaBoost parameters:", ABGrid.best_params_)
-print("Best AdaBoost score:", ABGrid.best_score_)
-ABBest = ABGrid.best_estimator_
-

Best AdaBoost parameters: {'learning_rate': 0.0625, 'n_estimators': 1000}
-Best AdaBoost score: 0.9475845410628019
-

fig, ax = plt.subplots()
-ax.set_xlabel("Iteration")
-ax.set_ylabel("Error")
-ax.set_title("Misclassification error for training and testing sets when using AdaBoost")
-ax.plot(1 - np.fromiter(ABBest.staged_score(X_train, y_train), float), label="train")
-ax.plot(1 - np.fromiter(ABBest.staged_score(X_test, y_test), float), label="test")
-ax.legend()
-plt.show()
-

SVCGrid = GridSearchCV(
-    SVC(),
-    {
-        "gamma": np.logspace(-7, -3, base=2, num=5),
-        "C": np.logspace(1, 5, base=2, num=5)
-    }
-).fit(X_train, y_train)
-

plotSearchGrid(SVCGrid, "C", "gamma")
-print("Best SVM parameters:", SVCGrid.best_params_)
-print("Best SVM score:", SVCGrid.best_score_)
-SVCBest = SVCGrid.best_estimator_
-

Best SVM parameters: {'C': 8.0, 'gamma': 0.0078125}
-Best SVM score: 0.8657004830917874
-

SVCGrid2 = GridSearchCV(
-    LinearSVC(),
-    {
-        "loss": ("hinge", "squared_hinge"),
-        "C": np.logspace(-15, -5, base=2, num=11)
-    }
-).fit(X_train, y_train)
-

plotSearchGrid(SVCGrid2, "C", "loss")
-print("Best LinearSVC parameters:", SVCGrid2.best_params_)
-print("Best LinearSVC score:", SVCGrid2.best_score_)
-LinearSVCBest = SVCGrid2.best_estimator_
-

Best LinearSVC parameters: {'C': 0.015625, 'loss': 'hinge'}
-Best LinearSVC score: 0.9031400966183576
-

print("Logistic Regression validation score:", LogRegBest.score(X_test, y_test))
-print("Random Forest       validation score:", RFBest.score(X_test, y_test))
-print("AdaBoost            validation score:", ABBest.score(X_test, y_test))
-print("SVM with rbf        validation score:", SVCBest.score(X_test, y_test))
-print("Linear SVC          validation score:", LinearSVCBest.score(X_test, y_test))
-

Logistic Regression validation score: 0.9501084598698482
-Random Forest       validation score: 0.9631236442516269
-AdaBoost            validation score: 0.9674620390455532
-SVM with rbf        validation score: 0.8937093275488069
-Linear SVC          validation score: 0.9175704989154013
-

# These variables store the true and predicted values so we don't need to recalculate them again and again.
-y_test_flat = np.ravel(y_test)
-LogRegPredict = LogRegBest.predict(X_test)
-RFPredict = RFBest.predict(X_test)
-ABPredict = ABBest.predict(X_test)
-SVCPredict = SVCBest.predict(X_test)
-LinearSVCPredict = LinearSVCBest.predict(X_test)
-

print("Logistic Regression precision score:", calculate_precision(y_test_flat, LogRegPredict))
-print("Random Forest       precision score:", calculate_precision(y_test_flat, RFPredict))
-print("AdaBoost            precision score:", calculate_precision(y_test_flat, ABPredict))
-print("SVM with rbf        precision score:", calculate_precision(y_test_flat, SVCPredict))
-print("Linear SVC          precision score:", calculate_precision(y_test_flat, LinearSVCPredict))
-

Logistic Regression precision score: 0.9481865284974094
-Random Forest       precision score: 0.9735449735449735
-AdaBoost            precision score: 0.9738219895287958
-SVM with rbf        precision score: 0.8808290155440415
-Linear SVC          precision score: 0.9247311827956989
-

print("Logistic Regression recall score:", calculate_recall(y_test_flat, LogRegPredict))
-print("Random Forest       recall score:", calculate_recall(y_test_flat, RFPredict))
-print("AdaBoost            recall score:", calculate_recall(y_test_flat, ABPredict))
-print("SVM with rbf        recall score:", calculate_recall(y_test_flat, SVCPredict))
-print("Linear SVC          recall score:", calculate_recall(y_test_flat, LinearSVCPredict))
-

Logistic Regression recall score: 0.9336734693877551
-Random Forest       recall score: 0.9387755102040817
-AdaBoost            recall score: 0.9489795918367347
-SVM with rbf        recall score: 0.8673469387755102
-Linear SVC          recall score: 0.8775510204081632
-

for label, pred in ("Logistic Regression", LogRegPredict), ("Random Forest", RFPredict), ("AdaBoost", ABPredict), ("SVM", SVCPredict), ("Linear SVC", LinearSVCPredict):
-    fpr, tpr, _ = roc_curve(y_test_flat, pred)
-    roc_auc = roc_auc_score(y_test_flat, pred)
-    plt.plot(fpr, tpr, label=f"micro-average ROC curve (AUC = {roc_auc})")
-    plt.title(f"ROC by {label}, AUC={roc_auc}")
-    plt.xlabel("False Positive Rate")
-    plt.ylabel("True Positive Rate")
-    plt.show()
-

-

Spam Email Classification¶

Cleaning¶

Can we do better?¶

Preparations¶

Importing packages¶

Import the data¶

Helpful functions¶

EDA¶

Model training¶

Logistic Regression¶

Feature ranking¶

Decision Tree Ensembles¶

SVMs¶

Results¶

Analysis, Discussion and Conclusion¶

Linear Regression¶

Ensembles¶

SVMs¶

Precision vs Recall¶

Takeaway¶