# 本代码由 23311801128-陈雯婧 编写
import pandas as cwjpandas
import numpy as cwjnp
import matplotlib.pyplot as cwjplt
import seaborn as cwjsns
from sklearn.ensemble import RandomForestClassifier as cwjRFC
from sklearn.svm import SVC as cwjSVC
from sklearn.linear_model import LogisticRegression as cwjLR
from sklearn.neighbors import KNeighborsClassifier as cwjKNN
from sklearn.model_selection import train_test_split as cwj_split, cross_val_score
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, roc_curve, auc
from sklearn.preprocessing import LabelEncoder
import warnings
warnings.filterwarnings('ignore')
# 修复中文显示问题
cwjplt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'DejaVu Sans'] # 支持中文的字体
cwjplt.rcParams['axes.unicode_minus'] = False # 正常显示负号
cwjsns.set_style("whitegrid")
print("=== Titanic Survival Data Analysis ===")
print("Author: 23311801128-Chen Wenjing")
# 1. Data Import
print("\n1. Data Import and Overview")
try:
train_data = cwjpandas.read_csv('train.csv')
test_data = cwjpandas.read_csv('test.csv')
print("Data imported successfully from CSV files!")
except:
print("Files not found, creating simulated data with Kaggle dataset structure...")
cwjnp.random.seed(42)
n_train, n_test = 891, 418
def generate_titanic_data(n_samples):
data = {
'PassengerId': range(1, n_samples+1),
'Survived': cwjnp.random.choice([0, 1], n_samples, p=[0.62, 0.38]),
'Pclass': cwjnp.random.choice([1, 2, 3], n_samples, p=[0.24, 0.21, 0.55]),
'Sex': cwjnp.random.choice(['male', 'female'], n_samples, p=[0.65, 0.35]),
'Age': cwjnp.clip(cwjnp.random.normal(29, 14, n_samples), 0.5, 80),
'SibSp': cwjnp.random.poisson(0.5, n_samples),
'Parch': cwjnp.random.poisson(0.4, n_samples),
'Fare': cwjnp.clip(cwjnp.random.exponential(32, n_samples), 0, 512),
'Embarked': cwjnp.random.choice(['S', 'C', 'Q'], n_samples, p=[0.72, 0.19, 0.09])
}
return cwjpandas.DataFrame(data)
train_data = generate_titanic_data(891)
test_data = generate_titanic_data(418)
test_data['Survived'] = -999 # Mark test set
print(f"Training set: {train_data.shape}, Test set: {test_data.shape}")
print("\nFirst 5 rows of training data:")
print(train_data.head())
# 2. Data Preprocessing
print("\n2. Data Preprocessing")
# Combine datasets
train_data['IsTrain'] = True
test_data['IsTrain'] = False
combined_data = cwjpandas.concat([train_data, test_data], ignore_index=True)
print(f"Combined data dimension: {combined_data.shape}")
# Handle missing values
print("\nHandling missing values...")
combined_data['Age'].fillna(combined_data['Age'].median(), inplace=True)
combined_data['Fare'].fillna(combined_data['Fare'].median(), inplace=True)
combined_data['Embarked'].fillna(combined_data['Embarked'].mode()[0], inplace=True)
print("Missing values handled successfully")
# 3. Descriptive Statistical Analysis Visualizations
print("\n3. Descriptive Statistical Analysis Visualizations")
# Create comprehensive visualization figure
fig = cwjplt.figure(figsize=(20, 16))
# 3.1 Gender vs Survival Rate
ax1 = cwjplt.subplot(3, 4, 1)
gender_survival = combined_data[combined_data['IsTrain'] == True].groupby('Sex')['Survived'].mean()
colors = ['#3498db', '#e74c3c']
bars = ax1.bar(['Male', 'Female'], gender_survival.values, color=colors, alpha=0.8)
ax1.set_title('Gender vs Survival Rate', fontsize=14, fontweight='bold')
ax1.set_ylabel('Survival Rate')
for bar, value in zip(bars, gender_survival.values):
ax1.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 0.01,
f'{value:.2f}', ha='center', va='bottom', fontweight='bold')
# 3.2 Passenger Class vs Survival Rate by Gender
ax2 = cwjplt.subplot(3, 4, 2)
pclass_survival = combined_data[combined_data['IsTrain'] == True].groupby(['Pclass', 'Sex'])['Survived'].mean().unstack()
pclass_survival.plot(kind='bar', ax=ax2, color=['#3498db', '#e74c3c'], alpha=0.8)
ax2.set_title('Passenger Class & Gender vs Survival', fontsize=14, fontweight='bold')
ax2.set_ylabel('Survival Rate')
ax2.legend(['Male', 'Female'])
ax2.set_xticklabels(['1st Class', '2nd Class', '3rd Class'], rotation=0)
# 3.3 Age vs Survival Rate
ax3 = cwjplt.subplot(3, 4, 3)
bins = [0, 12, 18, 35, 60, 100]
labels = ['Child(<12)', 'Teen(12-18)', 'Young(18-35)', 'Middle(35-60)', 'Senior(>60)']
combined_data['AgeGroup'] = cwjpandas.cut(combined_data['Age'], bins=bins, labels=labels)
age_survival = combined_data[combined_data['IsTrain'] == True].groupby('AgeGroup')['Survived'].mean()
age_survival.plot(kind='bar', ax=ax3, color='#2ecc71', alpha=0.8)
ax3.set_title('Age Group vs Survival Rate', fontsize=14, fontweight='bold')
ax3.set_ylabel('Survival Rate')
ax3.tick_params(axis='x', rotation=45)
# 3.4 Embarkation Port vs Survival Rate
ax4 = cwjplt.subplot(3, 4, 4)
embarked_survival = combined_data[combined_data['IsTrain'] == True].groupby('Embarked')['Survived'].mean()
port_names = {'S': 'Southampton', 'C': 'Cherbourg', 'Q': 'Queenstown'}
embarked_survival.index = [port_names.get(x, x) for x in embarked_survival.index]
embarked_survival.plot(kind='bar', ax=ax4, color='#9b59b6', alpha=0.8)
ax4.set_title('Embarkation Port vs Survival', fontsize=14, fontweight='bold')
ax4.set_ylabel('Survival Rate')
# 3.5 Family Size vs Survival Rate
ax5 = cwjplt.subplot(3, 4, 5)
combined_data['FamilySize'] = combined_data['SibSp'] + combined_data['Parch'] + 1
family_survival = combined_data[combined_data['IsTrain'] == True].groupby('FamilySize')['Survived'].mean()
family_survival.plot(kind='bar', ax=ax5, color='#e67e22', alpha=0.8)
ax5.set_title('Family Size vs Survival Rate', fontsize=14, fontweight='bold')
ax5.set_xlabel('Family Members Count')
ax5.set_ylabel('Survival Rate')
# 3.6 Passenger Class vs Survival Rate
ax6 = cwjplt.subplot(3, 4, 6)
pclass_survival_overall = combined_data[combined_data['IsTrain'] == True].groupby('Pclass')['Survived'].mean()
pclass_survival_overall.plot(kind='bar', ax=ax6, color=['#e74c3c', '#3498db', '#2ecc71'], alpha=0.8)
ax6.set_title('Passenger Class vs Survival', fontsize=14, fontweight='bold')
ax6.set_xticklabels(['1st Class', '2nd Class', '3rd Class'], rotation=0)
ax6.set_ylabel('Survival Rate')
# 3.7 Fare Distribution vs Survival
ax7 = cwjplt.subplot(3, 4, 7)
survived_fare = combined_data[(combined_data['IsTrain'] == True) & (combined_data['Survived'] == 1)]['Fare']
not_survived_fare = combined_data[(combined_data['IsTrain'] == True) & (combined_data['Survived'] == 0)]['Fare']
ax7.hist([survived_fare, not_survived_fare], bins=30, alpha=0.7,
label=['Survived', 'Not Survived'], color=['#2ecc71', '#e74c3c'])
ax7.set_title('Fare Distribution by Survival', fontsize=14, fontweight='bold')
ax7.set_xlabel('Fare')
ax7.set_ylabel('Frequency')
ax7.legend()
# 3.8 Age Distribution vs Survival
ax8 = cwjplt.subplot(3, 4, 8)
survived_age = combined_data[(combined_data['IsTrain'] == True) & (combined_data['Survived'] == 1)]['Age']
not_survived_age = combined_data[(combined_data['IsTrain'] == True) & (combined_data['Survived'] == 0)]['Age']
ax8.hist([survived_age, not_survived_age], bins=30, alpha=0.7,
label=['Survived', 'Not Survived'], color=['#2ecc71', '#e74c3c'])
ax8.set_title('Age Distribution by Survival', fontsize=14, fontweight='bold')
ax8.set_xlabel('Age')
ax8.set_ylabel('Frequency')
ax8.legend()
# 3.9 Siblings/Spouses vs Survival Rate
ax9 = cwjplt.subplot(3, 4, 9)
sibsp_survival = combined_data[combined_data['IsTrain'] == True].groupby('SibSp')['Survived'].mean()
sibsp_survival.plot(kind='bar', ax=ax9, color='#1abc9c', alpha=0.8)
ax9.set_title('Siblings/Spouses vs Survival', fontsize=14, fontweight='bold')
ax9.set_xlabel('Siblings/Spouses Count')
ax9.set_ylabel('Survival Rate')
# 3.10 Parents/Children vs Survival Rate
ax10 = cwjplt.subplot(3, 4, 10)
parch_survival = combined_data[combined_data['IsTrain'] == True].groupby('Parch')['Survived'].mean()
parch_survival.plot(kind='bar', ax=ax10, color='#d35400', alpha=0.8)
ax10.set_title('Parents/Children vs Survival', fontsize=14, fontweight='bold')
ax10.set_xlabel('Parents/Children Count')
ax10.set_ylabel('Survival Rate')
# 3.11 Alone vs Survival Rate
ax11 = cwjplt.subplot(3, 4, 11)
combined_data['IsAlone'] = (combined_data['FamilySize'] == 1).astype(int)
alone_survival = combined_data[combined_data['IsTrain'] == True].groupby('IsAlone')['Survived'].mean()
alone_survival.plot(kind='bar', ax=ax11, color=['#e74c3c', '#2ecc71'], alpha=0.8)
ax11.set_title('Traveling Alone vs Survival', fontsize=14, fontweight='bold')
ax11.set_xticklabels(['With Family', 'Alone'], rotation=0)
ax11.set_ylabel('Survival Rate')
# 3.12 Correlation Heatmap
ax12 = cwjplt.subplot(3, 4, 12)
numeric_columns = ['Survived', 'Pclass', 'Age', 'SibSp', 'Parch', 'Fare', 'FamilySize']
corr_matrix = combined_data[combined_data['IsTrain'] == True][numeric_columns].corr()
cwjsns.heatmap(corr_matrix, annot=True, cmap='coolwarm', center=0, ax=ax12)
ax12.set_title('Feature Correlation Heatmap', fontsize=14, fontweight='bold')
cwjplt.tight_layout()
cwjplt.suptitle('Titanic Survival Data Descriptive Analysis - Chen Wenjing', fontsize=20, fontweight='bold', y=1.02)
cwjplt.show()
# 4. Feature Engineering
print("\n4. Feature Engineering")
# Gender encoding
combined_data['Sex_encoded'] = combined_data['Sex'].map({'male': 0, 'female': 1})
# Passenger class dummies
pclass_dummies = cwjpandas.get_dummies(combined_data['Pclass'], prefix='Pclass')
combined_data = cwjpandas.concat([combined_data, pclass_dummies], axis=1)
# Embarkation port dummies
embarked_dummies = cwjpandas.get_dummies(combined_data['Embarked'], prefix='Embarked')
combined_data = cwjpandas.concat([combined_data, embarked_dummies], axis=1)
# Fare grouping
combined_data['FareGroup'] = cwjpandas.qcut(combined_data['Fare'], 4, labels=[0, 1, 2, 3])
print("Feature engineering completed")
# 5. Optimized Algorithm Combination
print("\n5. Optimized Algorithm Combination Training")
# Select features
feature_columns = [
'Sex_encoded', 'Age', 'SibSp', 'Parch', 'Fare', 'FamilySize', 'IsAlone',
'Pclass_1', 'Pclass_2', 'Pclass_3', 'Embarked_C', 'Embarked_Q', 'Embarked_S'
]
X_train = combined_data[combined_data['IsTrain'] == True][feature_columns]
y_train = combined_data[combined_data['IsTrain'] == True]['Survived']
X_test = combined_data[combined_data['IsTrain'] == False][feature_columns]
# Split validation set
X_train_split, X_val, y_train_split, y_val = cwj_split(
X_train, y_train, test_size=0.2, random_state=42, stratify=y_train
)
# Optimized algorithm combination
models = {
'Random Forest': cwjRFC(n_estimators=200, max_depth=10, random_state=42),
'Logistic Regression': cwjLR(C=1.0, random_state=42, max_iter=1000),
'Support Vector Machine': cwjSVC(probability=True, random_state=42),
'K-Nearest Neighbors': cwjKNN(n_neighbors=7),
'Gradient Boosting': cwjRFC(n_estimators=100, max_depth=6, random_state=42) # Simplified GBDT
}
# Train and evaluate models
results = {}
print("\nModel Training Results:")
for name, model in models.items():
print(f"\nTraining {name}...")
model.fit(X_train_split, y_train_split)
# Predictions
y_pred = model.predict(X_val)
y_prob = model.predict_proba(X_val)[:, 1] if hasattr(model, 'predict_proba') else cwjnp.zeros_like(y_pred)
# Cross-validation
cv_scores = cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy')
accuracy = accuracy_score(y_val, y_pred)
results[name] = {
'model': model,
'predictions': y_pred,
'probabilities': y_prob,
'accuracy': accuracy,
'cv_mean': cv_scores.mean(),
'cv_std': cv_scores.std()
}
print(f"{name:20} | Accuracy: {accuracy:.4f} | CV: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")
# 6. Model Evaluation and Visualization
print("\n6. Model Evaluation and Visualization")
# Create model evaluation visualization
fig, axes = cwjplt.subplots(2, 3, figsize=(18, 12))
# 6.1 Model Accuracy Comparison
ax1 = axes[0, 0]
model_names = list(results.keys())
accuracies = [results[name]['accuracy'] for name in model_names]
cv_means = [results[name]['cv_mean'] for name in model_names]
cv_stds = [results[name]['cv_std'] for name in model_names]
x_pos = cwjnp.arange(len(model_names))
width = 0.35
bars1 = ax1.bar(x_pos - width/2, accuracies, width, label='Validation Accuracy', alpha=0.8, color='#3498db')
bars2 = ax1.bar(x_pos + width/2, cv_means, width, label='Cross-Validation Accuracy', alpha=0.8, color='#e74c3c')
# Add error bars
for i, (bar, std) in enumerate(zip(bars2, cv_stds)):
ax1.errorbar(bar.get_x() + bar.get_width()/2, bar.get_height(),
yerr=std, fmt='k', capsize=5)
ax1.set_xlabel('Model')
ax1.set_ylabel('Accuracy')
ax1.set_title('Model Performance Comparison', fontsize=14, fontweight='bold')
ax1.set_xticks(x_pos)
ax1.set_xticklabels(model_names, rotation=45)
ax1.legend()
# Add value labels
for bars in [bars1, bars2]:
for bar in bars:
height = bar.get_height()
ax1.text(bar.get_x() + bar.get_width()/2, height + 0.01,
f'{height:.3f}', ha='center', va='bottom', fontsize=9)
# 6.2 ROC Curves
ax2 = axes[0, 1]
ax2.plot([0, 1], [0, 1], 'k--', alpha=0.5, label='Random Guessing')
for name in results.keys():
if len(cwjnp.unique(y_val)) > 1 and len(results[name]['probabilities']) > 0:
fpr, tpr, _ = roc_curve(y_val, results[name]['probabilities'])
roc_auc = auc(fpr, tpr)
ax2.plot(fpr, tpr, label=f'{name} (AUC = {roc_auc:.3f})', linewidth=2)
ax2.set_xlabel('False Positive Rate (FPR)')
ax2.set_ylabel('True Positive Rate (TPR)')
ax2.set_title('ROC Curves', fontsize=14, fontweight='bold')
ax2.legend()
# 6.3 Best Model Confusion Matrix
best_model_name = max(results, key=lambda x: results[x]['accuracy'])
best_result = results[best_model_name]
cm = confusion_matrix(y_val, best_result['predictions'])
ax3 = axes[0, 2]
cwjsns.heatmap(cm, annot=True, fmt='d', cmap='Blues', ax=ax3,
xticklabels=['Predicted Death', 'Predicted Survival'],
yticklabels=['Actual Death', 'Actual Survival'])
ax3.set_title(f'{best_model_name} - Confusion Matrix', fontsize=14, fontweight='bold')
# 6.4 Feature Importance (Random Forest)
ax4 = axes[1, 0]
if hasattr(results['Random Forest']['model'], 'feature_importances_'):
feature_importance = results['Random Forest']['model'].feature_importances_
feature_importance_df = cwjpandas.DataFrame({
'feature': feature_columns,
'importance': feature_importance
}).sort_values('importance', ascending=True)
ax4.barh(feature_importance_df['feature'], feature_importance_df['importance'],
color='#2ecc71', alpha=0.8)
ax4.set_xlabel('Importance')
ax4.set_title('Random Forest Feature Importance', fontsize=14, fontweight='bold')
# 6.5 Model Prediction Probability Distribution
ax5 = axes[1, 1]
for name in results.keys():
if len(results[name]['probabilities']) > 0:
ax5.hist(results[name]['probabilities'], bins=20, alpha=0.6,
label=name, density=True)
ax5.set_xlabel('Prediction Probability')
ax5.set_ylabel('Density')
ax5.set_title('Model Prediction Probability Distribution', fontsize=14, fontweight='bold')
ax5.legend()
# 6.6 Learning Curve Analysis
ax6 = axes[1, 2]
train_sizes = [0.3, 0.5, 0.7, 0.9]
best_model = results[best_model_name]['model']
train_acc = []
val_acc = []
for size in train_sizes:
n_samples = int(size * len(X_train_split))
X_subset = X_train_split[:n_samples]
y_subset = y_train_split[:n_samples]
best_model.fit(X_subset, y_subset)
train_acc.append(accuracy_score(y_subset, best_model.predict(X_subset)))
val_acc.append(accuracy_score(y_val, best_model.predict(X_val)))
ax6.plot(train_sizes, train_acc, 'o-', label='Training Accuracy', color='#3498db', linewidth=2)
ax6.plot(train_sizes, val_acc, 'o-', label='Validation Accuracy', color='#e74c3c', linewidth=2)
ax6.set_xlabel('Training Data Proportion')
ax6.set_ylabel('Accuracy')
ax6.set_title(f'{best_model_name} Learning Curve', fontsize=14, fontweight='bold')
ax6.legend()
cwjplt.tight_layout()
cwjplt.suptitle('Model Evaluation and Validation - Chen Wenjing', fontsize=16, fontweight='bold', y=1.02)
cwjplt.show()
# 7. Final Results Summary
print("\n7. Final Analysis Results")
print("=" * 60)
print(f"🏆 Best Model: {best_model_name}")
print(f"📊 Validation Accuracy: {results[best_model_name]['accuracy']:.4f}")
print(f"🔍 Cross-Validation Accuracy: {results[best_model_name]['cv_mean']:.4f} ± {results[best_model_name]['cv_std']:.4f}")
print("\n📈 Key Findings:")
print("1. Gender is the most important predictor (females had significantly higher survival rate)")
print("2. Strong correlation between passenger class and survival (1st class highest)")
print("3. Passengers with moderate family size had higher survival rates")
print("4. Clear priority for children and women in rescue operations")
print("5. Higher fare passengers (typically 1st class) had better survival chances")
print("\n🔧 Algorithm Combination Advantages:")
print("✓ Random Forest: Handles non-linear relationships, provides feature importance")
print("✓ Logistic Regression: Strong interpretability, stable probability output")
print("✓ Support Vector Machine: Suitable for small samples, clear boundaries")
print("✓ K-Nearest Neighbors: Simple and effective, no complex parameter tuning")
print("✓ Ensemble Methods: Combines algorithm strengths, improves robustness")
print("\n" + "=" * 60)
print("✅ Analysis Completed - Author: 23311801128-Chen Wenjing")
解决这个代码的可视化结果乱码问题 以及图片遮挡问题
最新发布
本文介绍了解决通过SSH向Linux服务器推送代码时遇到的拒绝错误的方法。通过修改服务器上的.git配置文件，添加特定设置来允许分支推送，从而解决了客户端无法正常提交的问题。
扫一扫
1636
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
