十大机器学习库，超全面总结！！-腾讯云开发者社区-腾讯云 (2024)

import tensorflow as tffrom tensorflow.keras.datasets import mnistfrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Dense, Flattenimport matplotlib.pyplot as plt# 加载数据(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train, x_test = x_train / 255.0, x_test / 255.0# 构建模型model = Sequential([ Flatten(input_shape=(28, 28)), Dense(128, activation='relu'), Dense(10, activation='softmax')])# 编译模型model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])# 训练模型history = model.fit(x_train, y_train, epochs=5, validation_data=(x_test, y_test))# 绘制训练结果plt.plot(history.history['accuracy'], label='accuracy')plt.plot(history.history['val_accuracy'], label = 'val_accuracy')plt.xlabel('Epoch')plt.ylabel('Accuracy')plt.ylim([0.5, 1])plt.legend(loc='lower right')plt.show()# 评估模型test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)print('\nTest accuracy:', test_acc)# Test accuracy: 0.9751999974250793

import torchimport torch.nn as nnimport torch.optim as optimfrom torchvision import datasets, transformsimport matplotlib.pyplot as plt# 数据加载和预处理transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])trainset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)testset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)# 定义模型class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.fc1 = nn.Linear(28 * 28, 128) self.fc2 = nn.Linear(128, 10) def forward(self, x): x = x.view(-1, 28 * 28) x = torch.relu(self.fc1(x)) x = self.fc2(x) return xmodel = Net()# 定义损失函数和优化器criterion = nn.CrossEntropyLoss()optimizer = optim.Adam(model.parameters(), lr=0.001)# 训练模型epochs = 5train_losses = []for epoch in range(epochs): running_loss = 0.0 for images, labels in trainloader: optimizer.zero_grad() outputs = model(images) loss = criterion(outputs, labels) loss.backward() optimizer.step() running_loss += loss.item() train_losses.append(running_loss / len(trainloader))# 绘制训练损失plt.plot(train_losses, label='Training loss')plt.xlabel('Epoch')plt.ylabel('Loss')plt.legend(loc='upper right')plt.show()# 评估模型correct = 0total = 0with torch.no_grad(): for images, labels in testloader: outputs = model(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item()print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))

import numpy as npimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn.svm import SVCfrom sklearn.decomposition import PCA# 加载数据iris = datasets.load_iris()X = iris.datay = iris.target# 数据预处理X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)scaler = StandardScaler()X_train = scaler.fit_transform(X_train)X_test = scaler.transform(X_test)# PCA降维pca = PCA(n_components=2)X_train_pca = pca.fit_transform(X_train)X_test_pca = pca.transform(X_test)# 训练模型svm = SVC(kernel='linear')svm.fit(X_train_pca, y_train)# 绘制决策边界def plot_decision_boundary(model, X, y): h = .02 x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1 y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1 xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) Z = model.predict(np.c_[xx.ravel(), yy.ravel()]) Z = Z.reshape(xx.shape) plt.contourf(xx, yy, Z, alpha=0.8) plt.scatter(X[:, 0], X[:, 1], c=y, edgecolors='k', marker='o') plt.xlabel('PCA Component 1') plt.ylabel('PCA Component 2') plt.title('Decision Boundary') plt.show()plot_decision_boundary(svm, X_test_pca, y_test)

from tensorflow.keras.datasets import mnistfrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Denseimport matplotlib.pyplot as plt# 加载数据(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train, x_test = x_train / 255.0, x_test / 255.0x_train = x_train.reshape(-1, 28, 28, 1)x_test = x_test.reshape(-1, 28, 28, 1)# 构建模型model = Sequential([ Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)), MaxPooling2D(pool_size=(2, 2)), Flatten(), Dense(128, activation='relu'), Dense(10, activation='softmax')])# 编译模型model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])# 训练模型history = model.fit(x_train, y_train, epochs=5, validation_data=(x_test, y_test))# 绘制训练结果plt.plot(history.history['accuracy'], label='accuracy')plt.plot(history.history['val_accuracy'], label = 'val_accuracy')plt.xlabel('Epoch')plt.ylabel('Accuracy')plt.ylim([0.5, 1])plt.legend(loc='lower right')plt.show()# 评估模型test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)print('\nTest accuracy:', test_acc)

import xgboost as xgbfrom xgboost import plot_importancefrom sklearn.datasets import load_bostonfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import mean_squared_errorimport matplotlib.pyplot as plt# 加载数据boston = load_boston()X = boston.datay = boston.target# 数据拆分X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)# 训练模型model = xgb.XGBRegressor(objective ='reg:squarederror', n_estimators=100)model.fit(X_train, y_train)# 预测y_pred = model.predict(X_test)mse = mean_squared_error(y_test, y_pred)print(f'Mean Squared Error: {mse}')# 绘制特征重要性plot_importance(model)plt.show()

import lightgbm as lgbfrom sklearn.datasets import load_breast_cancerfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scoreimport matplotlib.pyplot as plt# 加载数据data = load_breast_cancer()X = data.datay = data.target# 数据拆分X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)# 创建数据集train_data = lgb.Dataset(X_train, label=y_train)test_data = lgb.Dataset(X_test, label=y_test)# 参数设置params = { 'objective': 'binary', 'metric': 'binary_error', 'boosting_type': 'gbdt', 'num_leaves': 31, 'learning_rate': 0.05, 'feature_fraction': 0.9}# 训练模型bst = lgb.train(params, train_data, 100, valid_sets=[test_data], early_stopping_rounds=10)# 预测y_pred = bst.predict(X_test, num_iteration=bst.best_iteration)y_pred = (y_pred > 0.5).astype(int)accuracy = accuracy_score(y_test, y_pred)print(f'Accuracy: {accuracy}')# 绘制特征重要性lgb.plot_importance(bst)plt.show()

import nltkfrom nltk.tokenize import word_tokenizefrom nltk.corpus import stopwordsfrom nltk.stem import WordNetLemmatizerfrom nltk.sentiment.vader import SentimentIntensityAnalyzernltk.data.path.append('/Users/yaojianguo/nltk_data', '/Library/Frameworks/Python.framework/Versions/3.9/nltk_data', '/Library/Frameworks/Python.framework/Versions/3.9/share/nltk_data', '/Library/Frameworks/Python.framework/Versions/3.9/lib/nltk_data', '/usr/share/nltk_data', '/usr/local/share/nltk_data', '/usr/lib/nltk_data', '/usr/local/lib/nltk_data')# 下载 NLTK 的数据nltk.download('punkt')nltk.download('stopwords')nltk.download('wordnet')nltk.download('vader_lexicon')# 示例文本text = "NLTK is a great library for natural language processing. I use it all the time in my projects."# 分词tokens = word_tokenize(text.lower())# 去除停用词stop_words = set(stopwords.words('english'))filtered_tokens = [word for word in tokens if word.isalnum() and word not in stop_words]# 词形还原lemmatizer = WordNetLemmatizer()lemmatized_tokens = [lemmatizer.lemmatize(word) for word in filtered_tokens]# 构建文本processed_text = ' '.join(lemmatized_tokens)# 情感分析sid = SentimentIntensityAnalyzer()scores = sid.polarity_scores(processed_text)# 输出结果print("Text:", text)print("Sentiment Scores:", scores)

from gensim.models import Word2Vecfrom nltk.tokenize import word_tokenizeimport nltknltk.download('punkt')# 示例文本text = "NLTK is a great library for natural language processing. I use it all the time in my projects."# 分词tokens = word_tokenize(text.lower())# 构建 Word2Vec 模型model = Word2Vec([tokens], vector_size=100, window=5, min_count=1, sg=0)# 查找相似词similar_words = model.wv.most_similar('nltk')# 输出相似词print("Similar words to 'NLTK':", similar_words)

import numpy as npimport pandas as pdimport statsmodels.api as smimport matplotlib.pyplot as plt# 创建示例数据np.random.seed(0)X = 2 * np.random.rand(100, 1)y = 3 + 4 * X + np.random.randn(100, 1)# 将数据转换为 DataFramedf = pd.DataFrame({'X': X.flatten(), 'y': y.flatten()})# 添加截距项X = sm.add_constant(X)# 使用最小二乘法拟合线性回归模型model = sm.OLS(y, X).fit()# 打印模型摘要print(model.summary())# 绘制数据和拟合直线plt.scatter(X[:, 1], y, color='blue')plt.plot(X[:, 1], model.predict(X), color='red')plt.xlabel('X')plt.ylabel('y')plt.title('Linear Regression')plt.show()

import caffeimport numpy as npimport matplotlib.pyplot as plt# 设置 Caffe 模型和权重文件路径model_def = 'path/to/deploy.prototxt'model_weights = 'path/to/model.caffemodel'# 加载模型net = caffe.Net(model_def, model_weights, caffe.TEST)# 加载图像并进行预处理image = caffe.io.load_image('image.jpg')transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})transformer.set_transpose('data', (2,0,1))transformed_image = transformer.preprocess('data', image)# 将图像输入网络进行前向传播net.blobs['data'].data[...] = transformed_imageoutput = net.forward()# 获取预测结果output_prob = output['prob'][0] # 输出层名称为 'prob'predicted_class = np.argmax(output_prob)# 加载类别标签文件with open('path/to/labels.txt') as f: labels = f.readlines()# 显示图像和预测结果plt.imshow(image)plt.axis('off')plt.title('Predicted Class: ' + labels[predicted_class])plt.show()