首页下载资源人工智能时间序列异常检测相关代码

ZIP时间序列异常检测相关代码

weixin_442451881.72MB需要积分:1

资源文件列表:

KPIAnmalyDetect.zip 大约有91个文件
  1. KPIAnmalyDetect/
  2. KPIAnmalyDetect/.git/
  3. KPIAnmalyDetect/.git/COMMIT_EDITMSG 13B
  4. KPIAnmalyDetect/.git/config 250B
  5. KPIAnmalyDetect/.git/description 73B
  6. KPIAnmalyDetect/.git/HEAD 21B
  7. KPIAnmalyDetect/.git/hooks/
  8. KPIAnmalyDetect/.git/hooks/applypatch-msg.sample 478B
  9. KPIAnmalyDetect/.git/hooks/commit-msg.sample 896B
  10. KPIAnmalyDetect/.git/hooks/fsmonitor-watchman.sample 4.62KB
  11. KPIAnmalyDetect/.git/hooks/post-update.sample 189B
  12. KPIAnmalyDetect/.git/hooks/pre-applypatch.sample 424B
  13. KPIAnmalyDetect/.git/hooks/pre-commit.sample 1.6KB
  14. KPIAnmalyDetect/.git/hooks/pre-merge-commit.sample 416B
  15. KPIAnmalyDetect/.git/hooks/pre-push.sample 1.34KB
  16. KPIAnmalyDetect/.git/hooks/pre-rebase.sample 4.78KB
  17. KPIAnmalyDetect/.git/hooks/pre-receive.sample 544B
  18. KPIAnmalyDetect/.git/hooks/prepare-commit-msg.sample 1.46KB
  19. KPIAnmalyDetect/.git/hooks/push-to-checkout.sample 2.72KB
  20. KPIAnmalyDetect/.git/hooks/sendemail-validate.sample 2.25KB
  21. KPIAnmalyDetect/.git/hooks/update.sample 3.56KB
  22. KPIAnmalyDetect/.git/index 1.4KB
  23. KPIAnmalyDetect/.git/info/
  24. KPIAnmalyDetect/.git/info/exclude 240B
  25. KPIAnmalyDetect/.git/logs/
  26. KPIAnmalyDetect/.git/logs/HEAD 1.22KB
  27. KPIAnmalyDetect/.git/logs/refs/
  28. KPIAnmalyDetect/.git/logs/refs/heads/
  29. KPIAnmalyDetect/.git/logs/refs/heads/main 704B
  30. KPIAnmalyDetect/.git/objects/
  31. KPIAnmalyDetect/.git/objects/17/
  32. KPIAnmalyDetect/.git/objects/17/b5e7d565beafa42a2cd0953dbc1a78522fc162 1.7KB
  33. KPIAnmalyDetect/.git/objects/1b/
  34. KPIAnmalyDetect/.git/objects/1b/c18208157ff47e142215efc1c8453a3a3ee420 861B
  35. KPIAnmalyDetect/.git/objects/1d/
  36. KPIAnmalyDetect/.git/objects/1d/f235d02f5c89fde19bea84560e50d2c1aba2ed 568B
  37. KPIAnmalyDetect/.git/objects/29/
  38. KPIAnmalyDetect/.git/objects/29/84a226111e9062d53a20e6efd9fee7085ad056 125.86KB
  39. KPIAnmalyDetect/.git/objects/2c/
  40. KPIAnmalyDetect/.git/objects/2c/82a03e6eb026710532ce3d00a32183fe72fb61 160.67KB
  41. KPIAnmalyDetect/.git/objects/3d/
  42. KPIAnmalyDetect/.git/objects/3d/ea055931304295907b3f1f4936d3f6700c23b2 45KB
  43. KPIAnmalyDetect/.git/objects/3e/
  44. KPIAnmalyDetect/.git/objects/3e/6cbccba817f8567d1be18a227dcd15d6afce35 519B
  45. KPIAnmalyDetect/.git/objects/47/
  46. KPIAnmalyDetect/.git/objects/47/b626174f346b79c5e7e7e22fe9c61249f7d800 123B
  47. KPIAnmalyDetect/.git/objects/78/
  48. KPIAnmalyDetect/.git/objects/78/29311f0dc4c9b57d380a8f353196f6b7f43f96 1.21KB
  49. KPIAnmalyDetect/.git/objects/84/
  50. KPIAnmalyDetect/.git/objects/84/cbbefd43a1aed9c28c95fe9e6e88deb7864230 125.94KB
  51. KPIAnmalyDetect/.git/objects/88/
  52. KPIAnmalyDetect/.git/objects/88/ed2cfddd29cc16227680426828e106942e3ed1 1.82KB
  53. KPIAnmalyDetect/.git/objects/ad/
  54. KPIAnmalyDetect/.git/objects/ad/3f8692d0f4dd79acc3148aff0f0420405063f8 242.75KB
  55. KPIAnmalyDetect/.git/objects/bc/
  56. KPIAnmalyDetect/.git/objects/bc/e24835b88393abd6512775d9ccc9acf790b0e9 909B
  57. KPIAnmalyDetect/.git/objects/c7/
  58. KPIAnmalyDetect/.git/objects/c7/45fcee35a90c0de27e1db55859d9d89fc32d8e 620B
  59. KPIAnmalyDetect/.git/objects/d8/
  60. KPIAnmalyDetect/.git/objects/d8/141f7fd4aabbde9f48c957fcb5fbe2a28b289f 503B
  61. KPIAnmalyDetect/.git/objects/db/
  62. KPIAnmalyDetect/.git/objects/db/730e30b58ddcda997728b68a48efd528018ee0 742B
  63. KPIAnmalyDetect/.git/objects/e0/
  64. KPIAnmalyDetect/.git/objects/e0/119ddd1d1903a584450a2e0ddfb2d89987a8c3 118.69KB
  65. KPIAnmalyDetect/.git/objects/e3/
  66. KPIAnmalyDetect/.git/objects/e3/c126db3fd114f76b700645fbc6267e8b826347 1.17KB
  67. KPIAnmalyDetect/.git/objects/e4/
  68. KPIAnmalyDetect/.git/objects/e4/0ca1fb03d838e55163c783864ae9058d424087 116.76KB
  69. KPIAnmalyDetect/.git/objects/info/
  70. KPIAnmalyDetect/.git/objects/pack/
  71. KPIAnmalyDetect/.git/refs/
  72. KPIAnmalyDetect/.git/refs/heads/
  73. KPIAnmalyDetect/.git/refs/heads/main 41B
  74. KPIAnmalyDetect/.git/refs/tags/
  75. KPIAnmalyDetect/box.py 2.64KB
  76. KPIAnmalyDetect/data.csv 425.83KB
  77. KPIAnmalyDetect/data_balance.csv 569.81KB
  78. KPIAnmalyDetect/data_box.csv 543.96KB
  79. KPIAnmalyDetect/data_explore.ipynb 236.52KB
  80. KPIAnmalyDetect/data_k_means.csv 462.26KB
  81. KPIAnmalyDetect/data_normal.csv 543.96KB
  82. KPIAnmalyDetect/demo1_svm.py 1.15KB
  83. KPIAnmalyDetect/demo2_lstm.py 1.83KB
  84. KPIAnmalyDetect/demo2_lstm_.py 1.91KB
  85. KPIAnmalyDetect/demo3_k_means_.py 3.56KB
  86. KPIAnmalyDetect/demo4_iForest.py 751B
  87. KPIAnmalyDetect/demo5_anencoder.py 5.26KB
  88. KPIAnmalyDetect/demo6_one-class-SVM.py 1.42KB
  89. KPIAnmalyDetect/k_means_result.csv 336.78KB
  90. KPIAnmalyDetect/make_balance.py 737B
  91. KPIAnmalyDetect/normal.py 2.76KB

资源介绍:

时间序列异常检测代码
import os import pandas as pd import numpy as np import tensorflow as tf from sklearn import preprocessing import seaborn as sns sns.set(color_codes=True) import matplotlib.pyplot as plt def data_load(): # Load data set # 读取数据集 merged_data = pd.read_csv("data.csv", index_col='_time') print(merged_data.head()) #merged_data.plot() # Data pre-processing # Split the training and test sets merged_data=merged_data.sort_index(ascending=True) dataset_train,dataset_test=merged_data.iloc[:int(len(merged_data)*0.7)],merged_data.iloc[int(len(merged_data)*0.7):] #dataset_train.plot(figsize = (12,6)) """ Normalize data """ scaler = preprocessing.MinMaxScaler() # 归一化 X_train = pd.DataFrame(scaler.fit_transform(dataset_train), # Find the mean and standard deviation of X_train and apply them to X_train columns=dataset_train.columns, index=dataset_train.index) # Random shuffle training data X_train.sample(frac=1) X_test = pd.DataFrame(scaler.transform(dataset_test), columns=dataset_test.columns, index=dataset_test.index) return X_train,X_test # Build AutoEncoding model def AutoEncoder_build( X_train, act_func): tf.random.set_seed(10) # act_func = 'elu' # Input layer: model = tf.keras.Sequential() # Sequential() is a container that describes the network structure of the neural network, sequentially processing the model # First hidden layer, connected to input vector X. model.add(tf.keras.layers.Dense(10, activation=act_func, # activation function kernel_initializer='glorot_uniform', # Weight initialization kernel_regularizer=tf.keras.regularizers.l2(0.0), # Regularization to prevent overfitting input_shape=(X_train.shape[1],) ) ) model.add(tf.keras.layers.Dense(2, activation=act_func, kernel_initializer='glorot_uniform')) model.add(tf.keras.layers.Dense(10, activation=act_func, kernel_initializer='glorot_uniform')) model.add(tf.keras.layers.Dense(X_train.shape[1], kernel_initializer='glorot_uniform')) model.compile(loss='mse', optimizer='adam') # 设置编译器 print(model.summary()) tf.keras.utils.plot_model(model, show_shapes=True) return model def AutoEncoder_main(model, Epochs, BATCH_SIZE, validation_split): # Train model for 100 epochs, batch size of 10: # Epochs=100 # BATCH_SIZE=10 factor = 0.5 X_train,X_test=data_load() X_train_noise = X_train + factor * np.random.normal(0,1,size=X_train.shape) # 设置噪声 history = model.fit(np.array(X_train), np.array(X_train), batch_size=BATCH_SIZE, epochs=Epochs, validation_split=validation_split, # Training set ratio # shuffle=True, verbose=1) return history def plot_AE_history(history): plt.plot(history.history['loss'], 'b', label='Training loss') plt.plot(history.history['val_loss'], 'r', label='Validation loss') plt.legend(loc='upper right') plt.xlabel('Epochs') plt.ylabel('Loss, [mse]') plt.ylim([0,.1]) plt.show() plt.close() X_train,X_test=data_load() model=AutoEncoder_build( X_train, act_func='relu') history=AutoEncoder_main(model=model, Epochs=100, BATCH_SIZE=32, validation_split=0.5) plot_AE_history(history) X_pred = model.predict(np.array(X_train)) X_pred = pd.DataFrame(X_pred, columns=X_train.columns) X_pred.index = X_train.index scored = pd.DataFrame(index=X_train.index) scored['Loss_mae'] = np.mean(np.abs(X_pred-X_train), axis = 1) plt.figure() sns.distplot(scored['Loss_mae'], bins = 10, kde= True, color = 'blue') plt.xlim([0.0,.5]) plt.show() plt.close() X_pred = model.predict(np.array(X_test)) X_pred = pd.DataFrame(X_pred, columns=X_test.columns) X_pred.index = X_test.index threshod = 0.3 scored = pd.DataFrame(index=X_test.index) scored['Loss_mae'] = np.mean(np.abs(X_pred-X_test), axis = 1) scored['Threshold'] = threshod scored['Anomaly'] = scored['Loss_mae'] > scored['Threshold'] scored.head() X_pred_train = model.predict(np.array(X_train)) X_pred_train = pd.DataFrame(X_pred_train, columns=X_train.columns) X_pred_train.index = X_train.index scored_train = pd.DataFrame(index=X_train.index) scored_train['Loss_mae'] = np.mean(np.abs(X_pred_train-X_train), axis = 1) scored_train['Threshold'] = threshod scored_train['Anomaly'] = scored_train['Loss_mae'] > scored_train['Threshold'] scored = pd.concat([scored_train, scored]) scored.plot(logy=True, figsize = (10,6), ylim = [1e-2,1e2], color = ['blue','red']) plt.show() plt.close()
100+评论
captcha

    相关资源

    1. java swing项目购物系统mysql数据库-java课程设计毕业设计期末大作业

      csm2017#后端ZIP1.16MB4月前
      资源摘要:本资源为Java Swing项目购物系统，采用MySQL数据库，适用于Java课程设计、毕业设计以及期末大作业的学习参考。该系统使用Java Swing构建用户界面，结合JDBC与MySQL数据库实现商品查询、购物车管理等功能模块。该项目非常适合在校大学生进行参考与学习，同时为Java技术爱好者提供了极好的学习资源。通过本项目，用户可以深入学习Java图形界面编程和数据库操作的综合应用。

    2. java swing项目汽车租赁系统mysql数据库-java课程设计毕业设计期末大作业

      csm2017#后端ZIP1.19MB4月前
      资源摘要:本资源为Java Swing项目汽车租赁系统，基于MySQL数据库，适用于Java课程设计、毕业设计和期末大作业的学习参考。系统采用Java Swing构建用户友好的图形界面，结合JDBC和MySQL数据库实现车辆信息管理功能。该系统功能丰富，结构清晰，具有良好的可扩展性，便于学习与理解。非常适合在校大学生作为课程设计或毕业设计的参考项目，同时也是Java技术爱好者进行编程实践的理想素材。本项目可以帮助用户掌握Java图形界面编程和数据库交互的技术要点。

    3. javaweb项目高校教务管理系统springMVC+mysql-java课程设计毕业设计期末大作业

      csm2017#后端ZIP11.61MB4月前
      资源摘要:本项目是一个基于Spring MVC框架和MySQL数据库的高校教务管理系统，旨在为在校大学生的Java课程设计和毕业设计提供有价值的学习参考，帮助学生更好地理解和掌握Java Web开发技术。通过本项目，学习者可以深入了解Spring MVC的架构设计、MySQL数据库的操作以及如何构建一个功能完善的Web应用。

    4. w7-12-学生-第六讲 函数2.zip

      2302_82270948#行业研究ZIP2.19MB4月前
      资源摘要:w7-12-学生-第六讲 函数2.zip

    5. NodeJS期刊投稿信息查询系统-毕业设计源码06128（源码+数据库）

      DZBS2000#数据库ZIP14.78MB4月前
      资源摘要:基于微信小程序的期刊投稿信息查询系统有注册用户和管理员两个用户角色，下面针对两个用户角色的功能需求进行分析：1.注册用户：登录注册：用户可以注册新账号或使用已有账号登录。首页：展示系统的主要信息和功能入口。期刊信息：提供期刊的相关信息，包括期刊名称、投稿要求等。投稿信息：用户可以查看投稿相关的信息和要求。网站公告：显示系统发布的重要通知信息。我的：基本信息：用户可以查看和管理自己的基本信息。投稿信息：用户可以查看自己的投稿记录和状态。通知提醒：用户可以接收系统通知和提醒。2.管理员：后台首页：展示系统数据统计和管理入口。系统用户：管理系统中的各类用户。期刊信息管理：管理系统中期刊的相关信息。投稿信息管理：管理用户的投稿信息和处理投稿状态。通知提醒管理：发布、编辑和删除系统通知和提醒。轮播图管理：管理系统首页的轮播图内容。系统通知管理：管理系统发布的通知信息。权限管理：管理系统用户的权限和角色设置。这个系统旨在为投稿者和管理员提供一个便捷的投稿信息查询平台，同时管理员可以管理系统中的期刊信息、投稿信息和系统通知等内容，确保系统运行顺畅。

    6. nginx-upstream-fair-master

      m0_60821938#前端ZIP172.93KB4月前
      资源摘要:nginx-upstream-fair-master

    7. java swing项目费用报告系统mysql数据库-java课程设计毕业设计期末大作业

      csm2017#后端ZIP1.67MB4月前
      资源摘要:本资源为Java Swing项目费用报告系统，基于MySQL数据库，适合用于Java课程设计、毕业设计以及期末大作业的学习参考。系统采用Java Swing作为用户界面，结合JDBC与MySQL数据库实现数据的录入、编辑、删除、查询等功能。源码设计简洁明了、功能模块齐全，具有良好的可扩展性和学习参考价值，非常适合在校大学生进行参考和学习。该项目不仅帮助提升Java图形界面编程和数据库管理的能力，同时为Java技术爱好者提供了优质的学习素材。

    8. 11个代码生成相关的论文，20241022更新版本-持续更新，包含代码搜索、代码搜索、代码模型survey、代码评论评估、代码评

      sinat_37574187#人工智能ZIP14.86MB4月前
      资源摘要:find . -mindepth 2 -maxdepth 2 -type f -name "*.pdf" | awk -F/ '{print $(NF-1)}' | sort | uniq -c 2 代码或bug分类 1 代码搜索 1 代码生成 1 代码模型survey 1 代码评论评估 5 代码评估与提示
    站长QQ:九六九五七三七