12月初甘肃省AI竞赛心得记录

12月初甘肃省AI竞赛心得记录：

本次人工智能应用赛试题分为五部分：
1.人工智能开发环境的部署（机器学习/深度学习库的安装与测试）

2.样本数据预处理：将数据聚类并可视化，所给数据为10000个样本的特征数据，每一行表示一个样本的3维特征，将原始数据读取并在二维坐标轴上可视化；对数据进行聚类（聚为4类）；将聚类结果在二维坐标轴上可视化，每一类的数据需要用不同颜色进行区分。代码如下：

   from sklearn.datasets import make_circles
import matplotlib.pyplot as plt
import numpy as np
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
from sklearn.decomposition import PCA
import pandas as pd
import time
import functools

def time_cost(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        t0 = time.time()
        func(*args, **kwargs)
        t1 = time.time()
        print(args[0], '：%.2fs' % (t1 - t0))
        return func(*args, **kwargs), t1 - t0
    return wrapper

def load_data(file):
    assert file != ''
    df = pd.read_csv(r'C:\Users\yaya\Desktop\试题数据\第三部分\test.csv')
    x = df.values
    pca = PCA(n_components=2)
    pca_result = pca.fit_transform(x)
    return x, pca_result

@time_cost
def cluster_function(model_name, model, data):
    y_pred = model.fit_predict(data)
    return y_pred

if __name__ == '__main__':
    model_list = {  "KMeans": KMeans(n_clusters=4, random_state=10),  }
    x, pca_result = load_data(r'C:\Users\yaya\Desktop\试题数据\第三部分\test.csv')
    plt.scatter(pca_result[:, 0], pca_result[:, 1], marker='.')
    i = 1
    fig = plt.figure(figsize=(15, 10))
    for model in model_list:
        fig.add_subplot(2, 3, i)
        result = cluster_function(model, model_list[model], x)
        plt.scatter(pca_result[:, 0], pca_result[:, 1], marker='.', c=result[0])
        plt.title("{}({})".format(model, silhouette_score(x, result[0])))
        plt.text(.99, .01, ('%.2fs' % (result[1])).lstrip('0'), transform=plt.gca().transAxes,
                 horizontalalignment='right')
        i += 1
    plt.show()


```python
在这里插入代码片

3.统计词频并输出高频词汇
统计txt文件中出现频率最高的十个单词，输出对应的单词内容和频率。代码如下：

import string
file = open('./data.txt', 'r', encoding='UTF-8')

 创建一个字典用于存储每个单词出现的次数
word_appear_time = {}

sans_punctuation_documents = []
import string

for i in file:
    # TODO
    trantab = str.maketrans({key: None for key in string.punctuation})
    j = i.translate(trantab)
    sans_punctuation_documents.append(j)

 print (sans_punctuation_documents)

for line in sans_punctuation_documents:
    line = str.lower(line)
    words = line.strip().split()
    for word in words:
        if word in word_appear_time:
            word_appear_time[word] += 1
        else:
            word_appear_time[word] = 1

word_list = []
for word, times in word_appear_time.items():
    word_list.append((times, word))

word_list.sort(reverse=True)
for times, word in word_list[:10]:
    print(word, times)
    print(type(word))
print(word_list[:10])
print(type(word_list[:10]))
m = dict(word_list[:10])
mi = dict(zip(m.values(), m.keys()))
print(mi)

file.close()

4.深度学习算法应用：

resnet18网络模型
from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

plt.ion()   # interactive mode

data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = r'./data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features

model_ft.fc = nn.Linear(num_ftrs, 3)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()


optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)


exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=10)