学习python所有用来写ai的语句

在Python中编写AI程序通常涉及多个第三方库，如NumPy、Pandas、Scikit-learn、TensorFlow、PyTorch、Transformers等。由于每个库都提供了成千上万的函数、类和方法，不可能真正"穷举"所有语句。不过，我们可以按照AI开发的一般流程，分类列举其中最常用、最核心的语句示例，帮助你快速了解AI编程中常见的代码片段。

1. 导入常用库

python 复制代码

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# 机器学习
from sklearn import datasets, model_selection, preprocessing, metrics, linear_model, ensemble, neural_network

# 深度学习框架
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, models, optimizers, losses, metrics as tf_metrics

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import DataLoader, Dataset

# 自然语言处理
from transformers import AutoTokenizer, AutoModel, AutoModelForSequenceClassification, Trainer, TrainingArguments

2. 数据加载与预处理

python 复制代码

# 加载内置数据集（sklearn）
iris = datasets.load_iris()
X, y = iris.data, iris.target

# 读取外部数据（pandas）
df = pd.read_csv('data.csv')
df.head()

# 划分训练/测试集
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.2, random_state=42)

# 标准化
scaler = preprocessing.StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# 图像数据加载（torchvision）
from torchvision import datasets, transforms
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)

# 文本数据分词（transformers）
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
encoded = tokenizer("Hello world!", padding=True, truncation=True, return_tensors='pt')

3. 模型定义

Scikit-learn 模型

python 复制代码

model = linear_model.LogisticRegression()
model = ensemble.RandomForestClassifier(n_estimators=100)
model = neural_network.MLPClassifier(hidden_layer_sizes=(100, 50))

TensorFlow/Keras 模型

python 复制代码

# Sequential API
model = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dropout(0.2),
    layers.Dense(10, activation='softmax')
])

# Functional API
inputs = keras.Input(shape=(784,))
x = layers.Dense(128, activation='relu')(inputs)
outputs = layers.Dense(10, activation='softmax')(x)
model = keras.Model(inputs=inputs, outputs=outputs)

# 编译
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

PyTorch 模型

python 复制代码

class MyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 10)
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout(0.2)
    
    def forward(self, x):
        x = x.view(x.size(0), -1)
        x = self.relu(self.fc1(x))
        x = self.dropout(x)
        x = self.fc2(x)
        return x

model = MyModel()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

4. 损失函数与优化器

python 复制代码

# TensorFlow
loss_fn = losses.CategoricalCrossentropy()
optimizer = optimizers.Adam(learning_rate=0.001)

# PyTorch
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

5. 训练循环

Scikit-learn

python 复制代码

model.fit(X_train, y_train)

TensorFlow

python 复制代码

history = model.fit(X_train, y_train, batch_size=32, epochs=10, validation_split=0.2)

PyTorch（手动循环）

python 复制代码

for epoch in range(num_epochs):
    model.train()
    for inputs, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
    print(f'Epoch {epoch+1}, Loss: {loss.item():.4f}')

6. 评估与验证

Scikit-learn

python 复制代码

y_pred = model.predict(X_test)
accuracy = metrics.accuracy_score(y_test, y_pred)

TensorFlow

python 复制代码

test_loss, test_acc = model.evaluate(X_test, y_test)

PyTorch

python 复制代码

model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for inputs, labels in test_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    accuracy = correct / total

7. 模型保存与加载

python 复制代码

# TensorFlow
model.save('model.h5')
model = keras.models.load_model('model.h5')

# PyTorch
torch.save(model.state_dict(), 'model.pth')
model.load_state_dict(torch.load('model.pth'))

# Scikit-learn
import joblib
joblib.dump(model, 'model.pkl')
model = joblib.load('model.pkl')

8. 推理与预测

python 复制代码

# 一般形式
y_pred = model.predict(X_new)

# Hugging Face pipeline
from transformers import pipeline
classifier = pipeline('sentiment-analysis')
result = classifier("I love AI!")

9. 可视化与辅助工具

python 复制代码

# 绘图
plt.plot(history.history['loss'], label='train')
plt.plot(history.history['val_loss'], label='val')
plt.legend()
plt.show()

# 混淆矩阵
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
cm = confusion_matrix(y_test, y_pred)
ConfusionMatrixDisplay(cm).plot()

# 数据探查
df.describe()
df.info()
sns.pairplot(df, hue='species')

10. 其他常用库/语句

python 复制代码

# 图像处理（OpenCV）
import cv2
img = cv2.imread('image.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# 自然语言处理（NLTK）
import nltk
nltk.download('punkt')
tokens = nltk.word_tokenize("Hello world!")

# 强化学习（Gym）
import gym
env = gym.make('CartPole-v1')
obs = env.reset()
for _ in range(1000):
    action = env.action_space.sample()
    obs, reward, done, info = env.step(action)
    if done:
        obs = env.reset()

总结

以上列举了Python AI开发中最常用的语句，覆盖了数据准备、模型构建、训练、评估、推理等关键环节。由于AI领域涉及的库极其丰富，实际开发时可能还会用到更多特定的函数或方法，例如：

自定义层/损失函数
回调函数（TensorFlow Callbacks）
数据增强（Albumentations）
分布式训练（torch.distributed）
超参数调优（Optuna、Ray Tune）

如果你需要针对某个具体库或任务（如计算机视觉、NLP）的更详细语句列表，请进一步说明，我可以为你展开。