from collections import Counter def detect_outliers(df, n, features): outlier_indices = [] # iterate over features(columns) for col in features: # 1st quartile (25%) Q1 = np.percentile(df[col], 25) # 3rd quartile (75%) Q3 = np.percentile(df[col], 75) # Interquartile range (IQR) IQR = Q3 - Q1 # outlier step outlier_step = 1.5 * IQR # Determine a list of indices of outliers for feature col outlier_list_col = df[(df[col] < Q1 - outlier_step) | (df[col] > Q3 + outlier_step)].index # append the found outlier indices for col to the list of outlier indices outlier_indices.extend(outlier_list_col) # select observations containing more than 2 outliers outlier_indices = Counter(outlier_indices) multiple_outliers = list(k for k, v in outlier_indices.items() if v > n) return multiple_outliers Outliers_to_drop = detect_outliers(data, 0, list(data.columns)[-2:]) data = data.drop(Outliers_to_drop, axis=0).reset_index(drop=True) data

这段代码的作用是从Python的collections库中导入Counter，然后定义一个名为detect_outliers的函数，该函数需要传入三个参数：df、n和features。这个函数的作用是检测DataFrame中指定特征的离群值，并将它们的索引存储在outlier_indices列表中。