import pandas as pd import matplotlib.pyplot as plt import matplotlib as mpl import seaborn as sns sns.set_style("whitegrid") mpl.rcParams['figure.figsize'] = (20,5) dataframe = pd.read_csv(r'/work/Time_Series_Chemical_Machinery_Dataset.csv') dataframe.set_index("Date (DD/MM/YYYY)", inplace=True) ax1 = dataframe.plot(alpha=0.6) ax1.xaxis.set_major_locator(plt.MaxNLocator(10)) ax2 = ax1.twinx() ax2.plot(dataframe['Motor Trip Failure'],color='grey', marker='*') ax2.xaxis.set_major_locator(plt.MaxNLocator(10)) ax1.legend(bbox_to_anchor=(1.05, 1), loc='upper left') plt.title("Timeseries Plot of Chemical Machinery Data") plt.tight_layout() plt.show()

from adtk.detector import InterQuartileRangeAD from adtk.visualization import plot iqr_ad = InterQuartileRangeAD(c=1.5) example_df = pd.read_csv(r'/work/Time_Series_Chemical_Machinery_Dataset.csv', index_col="Date (DD/MM/YYYY)",parse_dates=True, dayfirst=True) column_names = example_df.drop('Motor Trip Failure', axis=1).columns for item in column_names: anomalies = iqr_ad.fit_detect(example_df[item]) plot(example_df[item], anomaly=anomalies, ts_linewidth=3, ts_markersize=3, anomaly_markersize=5, anomaly_color='deeppink', anomaly_tag="marker") example_df['Motor Trip Failure'].plot(color='black', marker="D", linewidth=1.5) plt.title(item) plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left') plt.tight_layout()

Q1 = example_df.quantile(0.25) Q3 = example_df.quantile(0.75) IQR = Q3 - Q1 Lower_Limit = Q1 - 1.5 * IQR Upper_Limit = Q3 + 1.5 * IQR No_Outliers_Dataframe = example_df[~((example_df < Lower_Limit) | ((example_df > Upper_Limit ))).any(axis=1)]

import plotly.express as px fig = px.box(No_Outliers_Dataframe[~No_Outliers_Dataframe['Motor Trip Failure']==1], title="Outliers Removed in the Chemical Machinery Dataset") fig.show() fig = px.box(example_df[example_df['Motor Trip Failure']==1], title="Outliers remaining in the Chemical Machinery Dataset") fig.show()