Software Defects Prediction using Machine Learning

This Python 3 environment comes with many helpful analytics libraries installed ## It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python ## For example, here's several helpful packages to load Step 1: Data Loading and Initial Analysis Handling Missing Values Step 4 : Model Building and Prediction Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse COMMAND_BLOCK: import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier from sklearn.svm import SVC from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score from sklearn.metrics import confusion_matrix, classification_report from sklearn.preprocessing import StandardScaler import warnings warnings.filterwarnings('ignore') # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier from sklearn.svm import SVC from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score from sklearn.metrics import confusion_matrix, classification_report from sklearn.preprocessing import StandardScaler import warnings warnings.filterwarnings('ignore') # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session COMMAND_BLOCK: import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier from sklearn.svm import SVC from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score from sklearn.metrics import confusion_matrix, classification_report from sklearn.preprocessing import StandardScaler import warnings warnings.filterwarnings('ignore') # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session COMMAND_BLOCK: # Load the Defects Dataset train = pd.read_csv('/kaggle/input/train.csv') test = pd.read_csv('/kaggle/input/test.csv') # Display first few rows print("First 5 rows of the training dataset:") print(train.head()) print("First 5 rows of the test dataset:") print(test.head()) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Load the Defects Dataset train = pd.read_csv('/kaggle/input/train.csv') test = pd.read_csv('/kaggle/input/test.csv') # Display first few rows print("First 5 rows of the training dataset:") print(train.head()) print("First 5 rows of the test dataset:") print(test.head()) COMMAND_BLOCK: # Load the Defects Dataset train = pd.read_csv('/kaggle/input/train.csv') test = pd.read_csv('/kaggle/input/test.csv') # Display first few rows print("First 5 rows of the training dataset:") print(train.head()) print("First 5 rows of the test dataset:") print(test.head()) COMMAND_BLOCK: # Dataset shape print(f"\nDataset Shape: {train.shape}") print(f"Number of samples: {train.shape[0]}") print(f"Number of features: {train.shape[1]}") print(f"\nDataset Shape: {test.shape}") print(f"Number of samples: {test.shape[0]}") print(f"Number of features: {test.shape[1]}") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Dataset shape print(f"\nDataset Shape: {train.shape}") print(f"Number of samples: {train.shape[0]}") print(f"Number of features: {train.shape[1]}") print(f"\nDataset Shape: {test.shape}") print(f"Number of samples: {test.shape[0]}") print(f"Number of features: {test.shape[1]}") COMMAND_BLOCK: # Dataset shape print(f"\nDataset Shape: {train.shape}") print(f"Number of samples: {train.shape[0]}") print(f"Number of features: {train.shape[1]}") print(f"\nDataset Shape: {test.shape}") print(f"Number of samples: {test.shape[0]}") print(f"Number of features: {test.shape[1]}") COMMAND_BLOCK: # Column names and data types print("\nColumn Information for training dataset:") print(train.info()) print("\nColumn Information for test datase t:") print(test.info()) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Column names and data types print("\nColumn Information for training dataset:") print(train.info()) print("\nColumn Information for test datase t:") print(test.info()) COMMAND_BLOCK: # Column names and data types print("\nColumn Information for training dataset:") print(train.info()) print("\nColumn Information for test datase t:") print(test.info()) COMMAND_BLOCK: # Statistical summary print("Statistical Summary:") print(train.describe()) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Statistical summary print("Statistical Summary:") print(train.describe()) COMMAND_BLOCK: # Statistical summary print("Statistical Summary:") print(train.describe()) CODE_BLOCK: #Get the statistical information about the training set import plotly.express as px train.describe().T\ .style.bar(subset=['mean'], color=px.colors.qualitative.G10[2])\ .background_gradient(subset=['std'], cmap='Blues')\ .background_gradient(subset=['50%'], cmap='Reds') Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: #Get the statistical information about the training set import plotly.express as px train.describe().T\ .style.bar(subset=['mean'], color=px.colors.qualitative.G10[2])\ .background_gradient(subset=['std'], cmap='Blues')\ .background_gradient(subset=['50%'], cmap='Reds') CODE_BLOCK: #Get the statistical information about the training set import plotly.express as px train.describe().T\ .style.bar(subset=['mean'], color=px.colors.qualitative.G10[2])\ .background_gradient(subset=['std'], cmap='Blues')\ .background_gradient(subset=['50%'], cmap='Reds') COMMAND_BLOCK: # Check for missing values print("=" * 50) print("Missing Values Analysis") print("=" * 50) missing = train.isnull().sum() missing_pct = (train.isnull().sum() / len(train)) * 100 missing_train = pd.DataFrame({ 'Missing_Count': missing, 'Missing_Percentage': missing_pct }) print(missing_train[missing_train['Missing_Count'] > 0]) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Check for missing values print("=" * 50) print("Missing Values Analysis") print("=" * 50) missing = train.isnull().sum() missing_pct = (train.isnull().sum() / len(train)) * 100 missing_train = pd.DataFrame({ 'Missing_Count': missing, 'Missing_Percentage': missing_pct }) print(missing_train[missing_train['Missing_Count'] > 0]) COMMAND_BLOCK: # Check for missing values print("=" * 50) print("Missing Values Analysis") print("=" * 50) missing = train.isnull().sum() missing_pct = (train.isnull().sum() / len(train)) * 100 missing_train = pd.DataFrame({ 'Missing_Count': missing, 'Missing_Percentage': missing_pct }) print(missing_train[missing_train['Missing_Count'] > 0]) COMMAND_BLOCK: # Check for duplicates print("=" * 50) print("Duplicate Analysis") print("=" * 50) duplicates = train.duplicated().sum() print(f"Number of duplicate rows: {duplicates}") print(f"\nDuplicate rows:") train[train.duplicated(keep=False)].sort_values('id') Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Check for duplicates print("=" * 50) print("Duplicate Analysis") print("=" * 50) duplicates = train.duplicated().sum() print(f"Number of duplicate rows: {duplicates}") print(f"\nDuplicate rows:") train[train.duplicated(keep=False)].sort_values('id') COMMAND_BLOCK: # Check for duplicates print("=" * 50) print("Duplicate Analysis") print("=" * 50) duplicates = train.duplicated().sum() print(f"Number of duplicate rows: {duplicates}") print(f"\nDuplicate rows:") train[train.duplicated(keep=False)].sort_values('id') COMMAND_BLOCK: # Check target variable distribution print("\nTarget Variable Distribution:") print(train['defects'].value_counts()) print(f"\nClass Balance:") print(train['defects'].value_counts(normalize=True)) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Check target variable distribution print("\nTarget Variable Distribution:") print(train['defects'].value_counts()) print(f"\nClass Balance:") print(train['defects'].value_counts(normalize=True)) COMMAND_BLOCK: # Check target variable distribution print("\nTarget Variable Distribution:") print(train['defects'].value_counts()) print(f"\nClass Balance:") print(train['defects'].value_counts(normalize=True)) COMMAND_BLOCK: # target value count defects_count = dict(train['defects'].value_counts()) defects_count Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # target value count defects_count = dict(train['defects'].value_counts()) defects_count COMMAND_BLOCK: # target value count defects_count = dict(train['defects'].value_counts()) defects_count CODE_BLOCK: #Check for missing (NaN) value print(train[train.isna().any(axis=1)]) Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: #Check for missing (NaN) value print(train[train.isna().any(axis=1)]) CODE_BLOCK: #Check for missing (NaN) value print(train[train.isna().any(axis=1)]) COMMAND_BLOCK: # visualize data distrubution fig , axis = plt.subplots(figsize = (25,35)) fig.suptitle('Data Distribution', ha = 'center', fontsize = 20, fontweight = 'bold',y=0.90 ) for idx,col in enumerate(list(train.columns)[1:-1]): plt.subplot(7,3,idx+1) ax = sns.histplot(train[col], color = 'blue' ,stat='density' , kde = False,bins = 50) sns.kdeplot(train[col] , color = 'orange' , ax = ax) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # visualize data distrubution fig , axis = plt.subplots(figsize = (25,35)) fig.suptitle('Data Distribution', ha = 'center', fontsize = 20, fontweight = 'bold',y=0.90 ) for idx,col in enumerate(list(train.columns)[1:-1]): plt.subplot(7,3,idx+1) ax = sns.histplot(train[col], color = 'blue' ,stat='density' , kde = False,bins = 50) sns.kdeplot(train[col] , color = 'orange' , ax = ax) COMMAND_BLOCK: # visualize data distrubution fig , axis = plt.subplots(figsize = (25,35)) fig.suptitle('Data Distribution', ha = 'center', fontsize = 20, fontweight = 'bold',y=0.90 ) for idx,col in enumerate(list(train.columns)[1:-1]): plt.subplot(7,3,idx+1) ax = sns.histplot(train[col], color = 'blue' ,stat='density' , kde = False,bins = 50) sns.kdeplot(train[col] , color = 'orange' , ax = ax) COMMAND_BLOCK: # adjust label names labels = ['not_defects', 'defects'] # visualize data target plt.title('Defects Values') sns.barplot(x = labels ,y = list(defects_count.values()), width = 0.3 , palette = ['blue' , 'orange']) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # adjust label names labels = ['not_defects', 'defects'] # visualize data target plt.title('Defects Values') sns.barplot(x = labels ,y = list(defects_count.values()), width = 0.3 , palette = ['blue' , 'orange']) COMMAND_BLOCK: # adjust label names labels = ['not_defects', 'defects'] # visualize data target plt.title('Defects Values') sns.barplot(x = labels ,y = list(defects_count.values()), width = 0.3 , palette = ['blue' , 'orange']) COMMAND_BLOCK: # visualize correlation corr = train.corr() mask = np.triu(np.ones_like(corr)) plt.figure(figsize = (20,10)) plt.title('Correlation Matrix') sns.heatmap(data = corr , mask = mask , annot = True , cmap = 'coolwarm',annot_kws={"color": "black", "size":9} ) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # visualize correlation corr = train.corr() mask = np.triu(np.ones_like(corr)) plt.figure(figsize = (20,10)) plt.title('Correlation Matrix') sns.heatmap(data = corr , mask = mask , annot = True , cmap = 'coolwarm',annot_kws={"color": "black", "size":9} ) COMMAND_BLOCK: # visualize correlation corr = train.corr() mask = np.triu(np.ones_like(corr)) plt.figure(figsize = (20,10)) plt.title('Correlation Matrix') sns.heatmap(data = corr , mask = mask , annot = True , cmap = 'coolwarm',annot_kws={"color": "black", "size":9} ) COMMAND_BLOCK: **Step 3 : Data cleaning and preparation** # convert target to binary encoder # Encode categorical variables from sklearn.preprocessing import LabelEncoder le = LabelEncoder() train['defects'] = le.fit_transform(train['defects']) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: **Step 3 : Data cleaning and preparation** # convert target to binary encoder # Encode categorical variables from sklearn.preprocessing import LabelEncoder le = LabelEncoder() train['defects'] = le.fit_transform(train['defects']) COMMAND_BLOCK: **Step 3 : Data cleaning and preparation** # convert target to binary encoder # Encode categorical variables from sklearn.preprocessing import LabelEncoder le = LabelEncoder() train['defects'] = le.fit_transform(train['defects']) CODE_BLOCK: train.defects.unique() Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: train.defects.unique() CODE_BLOCK: train.defects.unique() COMMAND_BLOCK: # Strategy 1: Fill missing values with mean/median train_cleaned = train.copy() print("Before filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) # Fill numeric missing values with median #train_cleaned['score'].fillna(train_cleaned['score'].median(), inplace=True) train_cleaned['i'].fillna(train_cleaned['i'].mean(), inplace=True) train_cleaned['b'].fillna(train_cleaned['b'].mean(), inplace=True) train_cleaned['lOBlank'].fillna(train_cleaned['lOBlank'].mean(), inplace=True) train_cleaned['uniq_Op'].fillna(train_cleaned['uniq_Op'].mean(), inplace=True) train_cleaned['total_Op'].fillna(train_cleaned['total_Op'].mean(), inplace=True) train_cleaned['branchCount'].fillna(train_cleaned['branchCount'].mean(), inplace=True) print("\nAfter filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Strategy 1: Fill missing values with mean/median train_cleaned = train.copy() print("Before filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) # Fill numeric missing values with median #train_cleaned['score'].fillna(train_cleaned['score'].median(), inplace=True) train_cleaned['i'].fillna(train_cleaned['i'].mean(), inplace=True) train_cleaned['b'].fillna(train_cleaned['b'].mean(), inplace=True) train_cleaned['lOBlank'].fillna(train_cleaned['lOBlank'].mean(), inplace=True) train_cleaned['uniq_Op'].fillna(train_cleaned['uniq_Op'].mean(), inplace=True) train_cleaned['total_Op'].fillna(train_cleaned['total_Op'].mean(), inplace=True) train_cleaned['branchCount'].fillna(train_cleaned['branchCount'].mean(), inplace=True) print("\nAfter filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) COMMAND_BLOCK: # Strategy 1: Fill missing values with mean/median train_cleaned = train.copy() print("Before filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) # Fill numeric missing values with median #train_cleaned['score'].fillna(train_cleaned['score'].median(), inplace=True) train_cleaned['i'].fillna(train_cleaned['i'].mean(), inplace=True) train_cleaned['b'].fillna(train_cleaned['b'].mean(), inplace=True) train_cleaned['lOBlank'].fillna(train_cleaned['lOBlank'].mean(), inplace=True) train_cleaned['uniq_Op'].fillna(train_cleaned['uniq_Op'].mean(), inplace=True) train_cleaned['total_Op'].fillna(train_cleaned['total_Op'].mean(), inplace=True) train_cleaned['branchCount'].fillna(train_cleaned['branchCount'].mean(), inplace=True) print("\nAfter filling missing values:") print(train_cleaned[['i', 'b','lOBlank','uniq_Op','total_Op','branchCount']].isnull().sum()) COMMAND_BLOCK: **Handling Outliers** # Visualize outliers using box plots plt.figure(figsize=(12,12)) i=1 for col in train.columns: plt.subplot(6,6,i) train[[col]].boxplot() i+=1 Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: **Handling Outliers** # Visualize outliers using box plots plt.figure(figsize=(12,12)) i=1 for col in train.columns: plt.subplot(6,6,i) train[[col]].boxplot() i+=1 COMMAND_BLOCK: **Handling Outliers** # Visualize outliers using box plots plt.figure(figsize=(12,12)) i=1 for col in train.columns: plt.subplot(6,6,i) train[[col]].boxplot() i+=1 COMMAND_BLOCK: # Detect outliers using IQR method def detect_outliers_iqr(data, column): Q1 = data[column].quantile(0.25) Q3 = data[column].quantile(0.75) IQR = Q3 - Q1 lower_bound = Q1 - 1.5 * IQR upper_bound = Q3 + 1.5 * IQR outliers = data[(data[column] < lower_bound) | (data[column] > upper_bound)] return outliers, lower_bound, upper_bound # Detect outliers in age outliers_b, lower_b, upper_b = detect_outliers_iqr(train_cleaned, 'b') print(f"b outliers (outside {lower_b:.2f} - {upper_b:.2f}):") print(outliers_b[['id', 'b']]) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Detect outliers using IQR method def detect_outliers_iqr(data, column): Q1 = data[column].quantile(0.25) Q3 = data[column].quantile(0.75) IQR = Q3 - Q1 lower_bound = Q1 - 1.5 * IQR upper_bound = Q3 + 1.5 * IQR outliers = data[(data[column] < lower_bound) | (data[column] > upper_bound)] return outliers, lower_bound, upper_bound # Detect outliers in age outliers_b, lower_b, upper_b = detect_outliers_iqr(train_cleaned, 'b') print(f"b outliers (outside {lower_b:.2f} - {upper_b:.2f}):") print(outliers_b[['id', 'b']]) COMMAND_BLOCK: # Detect outliers using IQR method def detect_outliers_iqr(data, column): Q1 = data[column].quantile(0.25) Q3 = data[column].quantile(0.75) IQR = Q3 - Q1 lower_bound = Q1 - 1.5 * IQR upper_bound = Q3 + 1.5 * IQR outliers = data[(data[column] < lower_bound) | (data[column] > upper_bound)] return outliers, lower_bound, upper_bound # Detect outliers in age outliers_b, lower_b, upper_b = detect_outliers_iqr(train_cleaned, 'b') print(f"b outliers (outside {lower_b:.2f} - {upper_b:.2f}):") print(outliers_b[['id', 'b']]) CODE_BLOCK: #List of numerical columns num_cols=[col for col in train.columns if (train[col].dtype in ["int64","float64"]) & (train[col].nunique()>50)] num_cols Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: #List of numerical columns num_cols=[col for col in train.columns if (train[col].dtype in ["int64","float64"]) & (train[col].nunique()>50)] num_cols CODE_BLOCK: #List of numerical columns num_cols=[col for col in train.columns if (train[col].dtype in ["int64","float64"]) & (train[col].nunique()>50)] num_cols COMMAND_BLOCK: #Method to handle outliers def handle_outliers( train, columns, factor=1.5, method="clip" # "clip" or "remove" ): """ Handle outliers using the IQR method. Parameters: train (pd.DataFrame): Input DataFrame columns (list): List of numeric columns factor (float): IQR multiplier (default 1.5) method (str): "clip" to cap values, "remove" to drop rows Returns: pd.DataFrame """ train = train.copy() for col in columns: Q1 = train[col].quantile(0.25) Q3 = train[col].quantile(0.75) IQR = Q3 - Q1 lower = Q1 - factor * IQR upper = Q3 + factor * IQR if method == "clip": train[col] = train[col].clip(lower, upper) elif method == "remove": train = train[(train[col] >= lower) & (train[col] <= upper)] else: raise ValueError("method must be 'clip' or 'remove'") return train Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: #Method to handle outliers def handle_outliers( train, columns, factor=1.5, method="clip" # "clip" or "remove" ): """ Handle outliers using the IQR method. Parameters: train (pd.DataFrame): Input DataFrame columns (list): List of numeric columns factor (float): IQR multiplier (default 1.5) method (str): "clip" to cap values, "remove" to drop rows Returns: pd.DataFrame """ train = train.copy() for col in columns: Q1 = train[col].quantile(0.25) Q3 = train[col].quantile(0.75) IQR = Q3 - Q1 lower = Q1 - factor * IQR upper = Q3 + factor * IQR if method == "clip": train[col] = train[col].clip(lower, upper) elif method == "remove": train = train[(train[col] >= lower) & (train[col] <= upper)] else: raise ValueError("method must be 'clip' or 'remove'") return train COMMAND_BLOCK: #Method to handle outliers def handle_outliers( train, columns, factor=1.5, method="clip" # "clip" or "remove" ): """ Handle outliers using the IQR method. Parameters: train (pd.DataFrame): Input DataFrame columns (list): List of numeric columns factor (float): IQR multiplier (default 1.5) method (str): "clip" to cap values, "remove" to drop rows Returns: pd.DataFrame """ train = train.copy() for col in columns: Q1 = train[col].quantile(0.25) Q3 = train[col].quantile(0.75) IQR = Q3 - Q1 lower = Q1 - factor * IQR upper = Q3 + factor * IQR if method == "clip": train[col] = train[col].clip(lower, upper) elif method == "remove": train = train[(train[col] >= lower) & (train[col] <= upper)] else: raise ValueError("method must be 'clip' or 'remove'") return train COMMAND_BLOCK: # Cap outliers print(f"Before outlier cleaning: {train_cleaned.shape}") train_cleaned = handle_outliers(train_cleaned, num_cols, method="clip") print(f"After outlier cleaning: {train_cleaned.shape}") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Cap outliers print(f"Before outlier cleaning: {train_cleaned.shape}") train_cleaned = handle_outliers(train_cleaned, num_cols, method="clip") print(f"After outlier cleaning: {train_cleaned.shape}") COMMAND_BLOCK: # Cap outliers print(f"Before outlier cleaning: {train_cleaned.shape}") train_cleaned = handle_outliers(train_cleaned, num_cols, method="clip") print(f"After outlier cleaning: {train_cleaned.shape}") COMMAND_BLOCK: # Separate features and target X= train_cleaned.drop("defects", axis=1) y= train_cleaned["defects"] X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.1, random_state = 42, stratify=y) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Separate features and target X= train_cleaned.drop("defects", axis=1) y= train_cleaned["defects"] X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.1, random_state = 42, stratify=y) COMMAND_BLOCK: # Separate features and target X= train_cleaned.drop("defects", axis=1) y= train_cleaned["defects"] X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.1, random_state = 42, stratify=y) COMMAND_BLOCK: # Initialize Random Forest Classifier rf_model = RandomForestClassifier( n_estimators=50, criterion='gini', max_depth=20, min_samples_split=10, min_samples_leaf=5, max_features='sqrt', bootstrap=True, random_state=42, n_jobs=-1 ) # Train the model rf_model.fit(X_train, y_train) print("Random Forest model trained successfully!") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Initialize Random Forest Classifier rf_model = RandomForestClassifier( n_estimators=50, criterion='gini', max_depth=20, min_samples_split=10, min_samples_leaf=5, max_features='sqrt', bootstrap=True, random_state=42, n_jobs=-1 ) # Train the model rf_model.fit(X_train, y_train) print("Random Forest model trained successfully!") COMMAND_BLOCK: # Initialize Random Forest Classifier rf_model = RandomForestClassifier( n_estimators=50, criterion='gini', max_depth=20, min_samples_split=10, min_samples_leaf=5, max_features='sqrt', bootstrap=True, random_state=42, n_jobs=-1 ) # Train the model rf_model.fit(X_train, y_train) print("Random Forest model trained successfully!") COMMAND_BLOCK: # Display model parameters print("\nModel Parameters:") print(rf_model.get_params()) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Display model parameters print("\nModel Parameters:") print(rf_model.get_params()) COMMAND_BLOCK: # Display model parameters print("\nModel Parameters:") print(rf_model.get_params()) COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) COMMAND_BLOCK: # Initialize Decision Tree Classifier dt_model = DecisionTreeClassifier( criterion='gini', max_depth=5, min_samples_split=20, min_samples_leaf=10, random_state=42 ) # Train the model dt_model.fit(X_train, y_train) print("Decision Tree model trained successfully!") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Initialize Decision Tree Classifier dt_model = DecisionTreeClassifier( criterion='gini', max_depth=5, min_samples_split=20, min_samples_leaf=10, random_state=42 ) # Train the model dt_model.fit(X_train, y_train) print("Decision Tree model trained successfully!") COMMAND_BLOCK: # Initialize Decision Tree Classifier dt_model = DecisionTreeClassifier( criterion='gini', max_depth=5, min_samples_split=20, min_samples_leaf=10, random_state=42 ) # Train the model dt_model.fit(X_train, y_train) print("Decision Tree model trained successfully!") CODE_BLOCK: from sklearn.tree import export_text tree_rules = export_text(dt_model) print(tree_rules) Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: from sklearn.tree import export_text tree_rules = export_text(dt_model) print(tree_rules) CODE_BLOCK: from sklearn.tree import export_text tree_rules = export_text(dt_model) print(tree_rules) COMMAND_BLOCK: # Make predictions y_train_pred = dt_model.predict(X_train) y_test_pred = dt_model.predict(X_test) print("Predictions completed!") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Make predictions y_train_pred = dt_model.predict(X_train) y_test_pred = dt_model.predict(X_test) print("Predictions completed!") COMMAND_BLOCK: # Make predictions y_train_pred = dt_model.predict(X_train) y_test_pred = dt_model.predict(X_test) print("Predictions completed!") COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) COMMAND_BLOCK: # Calculate accuracy scores train_accuracy = accuracy_score(y_train, y_train_pred) test_accuracy = accuracy_score(y_test, y_test_pred) print("=" * 50) print("Accuracy Scores") print("=" * 50) print(f"Training Accuracy: {train_accuracy:.4f} ({train_accuracy*100:.2f}%)") print(f"Testing Accuracy: {test_accuracy:.4f} ({test_accuracy*100:.2f}%)") print("=" * 50) CODE_BLOCK: #linear Regression def lr(X_train, X_test, y_train, y_test): model = LinearRegression() model.fit(X_train, y_train.values.ravel()) y_pred = model.predict(X_test) error = mean_squared_error(y_test, y_pred) print(f"Score: {error}") return model Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: #linear Regression def lr(X_train, X_test, y_train, y_test): model = LinearRegression() model.fit(X_train, y_train.values.ravel()) y_pred = model.predict(X_test) error = mean_squared_error(y_test, y_pred) print(f"Score: {error}") return model CODE_BLOCK: #linear Regression def lr(X_train, X_test, y_train, y_test): model = LinearRegression() model.fit(X_train, y_train.values.ravel()) y_pred = model.predict(X_test) error = mean_squared_error(y_test, y_pred) print(f"Score: {error}") return model CODE_BLOCK: #Submission X_test = test[X_train.columns] y_test_pred = rf_model.predict(X_test) submission = pd.DataFrame({ "id": test["id"], "defects": y_test_pred }) submission.to_csv("submission.csv", index=False) submission Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: #Submission X_test = test[X_train.columns] y_test_pred = rf_model.predict(X_test) submission = pd.DataFrame({ "id": test["id"], "defects": y_test_pred }) submission.to_csv("submission.csv", index=False) submission CODE_BLOCK: #Submission X_test = test[X_train.columns] y_test_pred = rf_model.predict(X_test) submission = pd.DataFrame({ "id": test["id"], "defects": y_test_pred }) submission.to_csv("submission.csv", index=False) submission