pre_processing_insights.py

# imports
import os
import pandas as pd
import numpy as np
import seaborn as sns
sns.set(color_codes=True)
import matplotlib.pyplot as plt


data_dir = 'Here place the location of unzipped BearingData Set2 folder'
merged_data = pd.DataFrame()

for filename in os.listdir(data_dir):

    dataset=pd.read_csv(os.path.join(data_dir, filename), sep='\t')
    dataset_mean_abs = np.array(dataset.abs().mean())
    dataset_mean_abs = pd.DataFrame(dataset_mean_abs.reshape(1,4))
    dataset_mean_abs.index = [filename]
    merged_data = merged_data.append(dataset_mean_abs)

merged_data.columns = ['Bearing 1','Bearing 2','Bearing 3','Bearing 4']
merged_data.index = pd.to_datetime(merged_data.index, format='%Y.%m.%d.%H.%M.%S')
merged_data = merged_data.sort_index()
merged_data.to_csv('./dataset/dataset_Bearing_rough.csv')
merged_data.head()


dataset_train = merged_data['2004-02-12 11:02:39':'2004-02-13 23:52:39']
dataset_test = merged_data['2004-02-13 23:52:39':]
dataset_train.plot(figsize = (12,6))
plt.show()
dataset_test.plot(figsize = (12,6))
plt.show()