为什么在我尝试实现带通巴特沃斯滤波器时输出信号与输入信号相同？

Question

这是我的代码：

def mask(mask_cols):
    """
    This function masks specific columns of the pupil dataframe.
    """
    masked_df = pd.read_csv(con.CLEANED_PUPIL_GAZE)

    masked_df = mask_pupil_first_derivative(masked_df, threshold=3.0,
                                mask_cols=['diameter', 'diameter_3d'])

    return masked_df


def smooth(columns_to_smooth):
    """
    This function smooths two columns of the interpolated pupil dataframe.
    :param columns_to_smooth: diameter and diamete 3d columns.
    """
    original_df = mask(mask_cols=['diameter', 'diameter_3d'])

    smooth_df = original_df

    logging.basicConfig(filename='filtering_errors.log', level=logging.ERROR)

    print(smooth_df)

    print("Data will be now be smoothed with a low-pass BW filter.")

    nyquist = 0.5 * con.sample_rate_ET
    cutoff_high = 4.0 # Example: Upper bound for smoothing
    cutoff_low = 0.01  # Example: Lower bound for smoothing

    # Calculate normalized cutoff frequencies
    normalized_cutoff_low = cutoff_low / nyquist
    normalized_cutoff_high = cutoff_high / nyquist

    for column in columns_to_smooth:
        try:
            # Check for NaNs before filtering
            if smooth_df[column].isnull().any():
                raise ValueError(f"NaN values detected in column {column} before filtering")

            # Apply Butterworth filter to the selected column
            b, a = butter(N=3, Wn=[normalized_cutoff_low, normalized_cutoff_high],
                          btype='bandpass', fs=con.sample_rate_ET)
            smooth_values = filtfilt(b, a, smooth_df[column])

            # Check for NaNs after filtering
            if np.isnan(smooth_values).any():
                raise ValueError(f"NaN values detected after filtering column {column}")

            # Update the column in smooth_df with the filtered values
            smooth_df[column] = smooth_values

            print(smooth_values)

        except ValueError as e:
            print(f"Error: {e}")
            # Handle the error, e.g., log the error, skip this column, or set NaNs as appropriate

    # Save the smoothed data to a new CSV file
    smooth_df.to_csv(con.SMOOTHED_PUPIL, index=False)

    # Plot the frequency response of the filter for the current column
    w, h = freqs(b, a)
    plt.semilogx(w, 20 * np.log10(abs(h)))
    plt.title(f'Butterworth filter frequency response for column {column}')
    plt.xlabel('Frequency [radians / second]')
    plt.ylabel('Amplitude [dB]')
    plt.margins(0, 0.1)
    plt.grid(which='both', axis='both')
    plt.axvline(100, color='green')  # cutoff frequency
    plt.show()

    # Assuming 'original_df' contains the original data before smoothing and 'smooth_df' contains the smoothed data
    # Plot original and smoothed data for comparison
    plt.plot(original_df['pupil_timestamp'], original_df['diameter'], label='Original')
    plt.plot(smooth_df['pupil_timestamp'], smooth_df['diameter'], label='Smoothed')
    plt.xlabel('Timestamp')
    plt.ylabel('Diameter')
    plt.title('Comparison of Original and Smoothed Data')
    plt.legend()
    plt.show()

    # Calculate summary statistics
    original_mean = original_df['diameter'].mean()
    smoothed_mean = smooth_df['diameter'].mean()

    original_std = original_df['diameter'].std()
    smoothed_std = smooth_df['diameter'].std()

    # Print summary statistics
    print(f"Original Mean: {original_mean}, Smoothed Mean: {smoothed_mean}")
    print(f"Original Standard Deviation: {original_std}, Smoothed Standard Deviation: {smoothed_std}")

我正在处理平均采样率为 120 Hz 的眼动追踪数据（但每个数据集可能有所不同）。原始数据集和平滑数据集具有相同的均值和标准差，并且图形重叠。

没有进行平滑处理。我该怎么办？

Answer 1

正如 @mkrieger1 指出的那样，您没有制作 pandas 数据框的深层副本。这就是您面临此问题的原因。如果您参考这篇post，您就知道您的逻辑应该是

smoothed_df = original_df.copy(deep=True)

这应该确保您的答案是不同的。否则，您将根据同一数据帧计算统计数据。