predictorWeekly.py 文件源码

def knnPredictor(df):

    dataTrainX, dataTrainY, dataTestX, dataTestY = sample(df)
    corelationCoefficiantDictionary = {}
    corelationCoefficiantArray = []

    for k in range(1, 200, 1):
        knnModel = KNeighborsRegressor(n_neighbors=k)

        knnModel.fit(dataTrainX, dataTrainY)

        knnpredicted = knnModel.predict(dataTestX)
        corelationCoefficient = pearsonr(dataTestY, knnpredicted)
        corelationCoefficiantDictionary[k] = corelationCoefficient[0]
        corelationCoefficiantArray.append(corelationCoefficient[0])

    # plotter.plot(corelationCoefficiantArray)
    bestK = max(corelationCoefficiantDictionary, key=corelationCoefficiantDictionary.get)

    knnModelBest = KNeighborsRegressor(n_neighbors=bestK)
    knnModelBest.fit(dataTrainX, dataTrainY)
    print("K = ")
    print(bestK)
    print("Corelation Coeff:")
    print(corelationCoefficiantDictionary[bestK])

    knnpredictedBest = knnModelBest.predict(dataTestX)

    fig, ax = plotter.subplots()
    corelationCoefficient = pearsonr(dataTestY, knnpredictedBest)
    print(corelationCoefficient[0])
    ax.set_ylabel('Predicted KNN Weekly')
    ax.scatter(dataTestY, knnpredictedBest)
    ax.set_xlabel('Measured')
    plotter.show()