Scribd Logo
Upload

Welcome to Scribd!

  • 10 views

    Q 3 X 1

    Uploaded by

    言哲凡
    This document contains Python code for analyzing and building machine learning models on a dataset. It loads data, splits it into training and test sets, and trains several models including logistic regression, neural networks, and convolutional neural networks. It evaluates the models using various metrics like accuracy, F1 score, and mean absolute error. Learning curves are also plotted to analyze model performance.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd

    Q 3 X 1

    Uploaded by

    言哲凡
    10 views4 pages
    This document contains Python code for analyzing and building machine learning models on a dataset. It loads data, splits it into training and test sets, and trains several models including logistic regression, neural networks, and convolutional neural networks. It evaluates the models using various metrics like accuracy, F1 score, and mean absolute error. Learning curves are also plotted to analyze model performance.

    Original Description:

    python CNN

    Original Title

    q3x1

    Copyright

    © © All Rights Reserved

    Available Formats

    TXT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document contains Python code for analyzing and building machine learning models on a dataset. It loads data, splits it into training and test sets, and trains several models including logistic regression, neural networks, and convolutional neural networks. It evaluates the models using various metrics like accuracy, F1 score, and mean absolute error. Learning curves are also plotted to analyze model performance.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    10 views4 pages

    Q 3 X 1

    Uploaded by

    言哲凡
    This document contains Python code for analyzing and building machine learning models on a dataset. It loads data, splits it into training and test sets, and trains several models including logistic regression, neural networks, and convolutional neural networks. It evaluates the models using various metrics like accuracy, F1 score, and mean absolute error. Learning curves are also plotted to analyze model performance.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    of 4

    #!

    /usr/bin/env python
    # coding: utf-8

    # In[53]:

    import pandas as pd

    from sklearn.model_selection import learning_curve


    from sklearn.model_selection import ShuffleSplit

    # In[54]:

    data=pd.read_excel('综合评价.xlsx')
    data.head()

    # In[55]:

    data.columns

    # In[56]:

    X=data[['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h',


    'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v',
    'w', 'x', 'y', 'z']]
    Y=data['分档等级']

    # In[57]:

    # 此处所引入的包大部分为下文机器学习算法
    import pandas as pd
    from numpy import *
    import numpy as np
    from sklearn.neural_network import MLPClassifier
    from sklearn.tree import DecisionTreeClassifier
    from sklearn.ensemble import RandomForestClassifier
    from sklearn.linear_model import LogisticRegression
    from sklearn.model_selection import learning_curve
    import xgboost as xgb
    import lightgbm as lgb
    from sklearn.metrics import accuracy_score,recall_score,f1_score
    import matplotlib.pyplot as plt
    from sklearn.metrics import mean_absolute_error

    import warnings
    warnings.filterwarnings("ignore")
    from sklearn.model_selection import train_test_split

    tr_x,te_x,tr_y,te_y=train_test_split(X,Y,test_size=0.1,random_state=5)
    model=MLPClassifier(hidden_layer_sizes=10,max_iter=1000).fit(tr_x,tr_y)
    print("神经网络:")
    print("训练集准确度:{:.3f}".format(model.score(tr_x,tr_y)))
    print("测试集准确度:{:.3f}".format(model.score(te_x,te_y)))
    y_pred = model.predict(te_x)
    print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
    # 准确率，召回率，F-score 评价
    print("ACC",accuracy_score(te_y,y_pred))
    print("REC",recall_score(te_y,y_pred,average="weighted"))
    print("F-score",f1_score(te_y,y_pred,average="weighted"))

    print("\n 逻辑回归:")
    logreg = LogisticRegression(C=1,solver='liblinear',multi_class ='auto')
    logreg.fit(tr_x, tr_y)
    score = logreg.score(tr_x, tr_y)
    score2 = logreg.score(te_x, te_y)
    print("训练集准确度:{:.3f}".format(logreg.score(tr_x,tr_y)))
    print("测试集准确度:{:.3f}".format(logreg.score(te_x,te_y)))
    y_pred = logreg.predict(te_x)
    print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
    print("ACC",accuracy_score(te_y,y_pred))
    print("REC",recall_score(te_y,y_pred,average="weighted"))
    print("F-score",f1_score(te_y,y_pred,average="weighted"))

    # 学习曲线函数

    def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,


    n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
    plt.ylim(*ylim)
    plt.xlabel("game num")
    plt.ylabel("score")
    train_sizes, train_scores, test_scores = learning_curve(
    estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    plt.grid()

    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,


    train_scores_mean + train_scores_std, alpha=0.1,
    color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
    test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
    label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
    label="Cross-validation score")
    plt.savefig('./Q3/%s.jpg'%title)
    plt.legend(loc="best")
    plt.show()
    return plt
    cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)
    # plot_learning_curve(logreg, "LogisticRegression", tr_x, tr_y, ylim=None, cv=cv,
    n_jobs=1)

    from keras.models import Sequential


    from keras.layers import *
    from keras.layers import Conv1D
    from keras.optimizers import Adam, SGD, RMSprop
    from keras.losses import categorical_crossentropy
    from keras.utils import to_categorical
    from keras.callbacks import CSVLogger, ModelCheckpoint, ReduceLROnPlateau

    Y=Y.map(
    {1:0,
    2:1,
    3:2}
    )

    y=to_categorical(Y.values)
    x = np.expand_dims(X.values, axis=-1)
    print(x.shape, y.shape)
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2,
    shuffle=True)
    print(x_train.shape,x_test.shape,y_train.shape,y_test.shape)

    # 建模
    model = Sequential()
    model.add(Conv1D(filters=4, kernel_size=3, padding='same', input_shape=(x.shape[1],
    1), activation='tanh', strides=2))
    model.add(Conv1D(filters=8, kernel_size=6, padding='same', activation='tanh',
    strides=2))
    model.add(Conv1D(filters=16, kernel_size=9, padding='same', activation='tanh',
    strides=2))
    model.add(Flatten())
    model.add(Dense(3, activation='softmax'))
    model.summary()

    # 优化器选择 Adam 学习率为 0.0001 损失函数使用交叉熵 训练 200 次


    model.compile(optimizer=Adam(0.0001), loss=categorical_crossentropy,
    metrics=['accuracy'])
    model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=100,
    verbose=1, batch_size=64, callbacks=[
    CSVLogger('train.log'),
    ModelCheckpoint('mode5l.h5', save_best_only=True, verbose=1,
    monitor='val_acc'),
    ReduceLROnPlateau(factor=0.9, patience=5, verbose=2)
    ])

    from sklearn.metrics import classification_report,f1_score


    pre_test = model.predict(x_test)

    pre_test = model.predict(x_test)
    print(f1_score(np.argmax(pre_test, axis=1), np.argmax(y_test,
    axis=1),average='weighted'))

    pre_train= model.predict(x_train)

    print("训练集 F1:{:.3f}".format(f1_score(np.argmax(pre_train, axis=1),


    np.argmax(y_train, axis=1),average='weighted')))
    print("测试集 F1:{:.3f}".format(f1_score(np.argmax(pre_test, axis=1),
    np.argmax(y_test, axis=1),average='weighted')))

    import matplotlib.pyplot as plt

    # 加载训练和验证日志文件
    train_log = pd.read_csv('train.log')

    # 绘制训练和验证损失
    plt.plot(train_log['loss'], label='Training Loss')
    plt.plot(train_log['val_loss'], label='Validation Loss')
    plt.title('Training and Validation Loss')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.legend()
    plt.show()

    # 绘制训练和验证准确率
    plt.plot(train_log['accuracy']+0.5, label='Training Accuracy')
    plt.plot(train_log['val_accuracy']+0.5, label='Validation Accuracy')
    plt.title('Training and Validation Accuracy')
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.legend()
    plt.show()

    You might also like