KUSAL BERA kusal1990
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| df_signal_train.isnull().sum().sum() |
kusal1990
/ Prediction on the test dataset
Last active
June 2, 2022 07:49
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| preds_test = [] | |
| for i in range(N_SPLITS): | |
| model.load_weights('weights_{}.h5'.format(i)) | |
| pred = model.predict(X_test_input, batch_size=300, verbose=1) | |
| pred_3 = [] | |
| for pred_scalar in pred: | |
| for i in range(3): | |
| pred_3.append(pred_scalar) | |
| preds_test.append(pred_3) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # to open/create a new html file in the write mode | |
| f = open('index8050.html', 'w') | |
| # the html code which will go in the file GFG.html | |
| html_template = """<html> | |
| <head> | |
| <title></title> | |
| </head> | |
| <body> | |
| <h2>VSB Power Line Fault Detection:Classification</h2> |
kusal1990
/ Examining phase and target.py
Created
June 2, 2022 18:07
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| subplot = sns.countplot(x='target', data=df_metadata_train) | |
| # https://github.com/mwaskom/seaborn/issues/1582 | |
| for i,j in enumerate(subplot.patches): | |
| percent = np.round((df_metadata_train[df_metadata_train['target']==i].shape[0]/df_metadata_train['target'].shape[0])*100, 2) | |
| subplot.annotate(str(df_metadata_train[df_metadata_train['target']==i].shape[0]) + f" ({percent}%)", | |
| (j.get_x()+j.get_width()/2, j.get_height())) | |
| plt.title("Distribution of target classes") | |
| plt.show() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| sns.countplot(x = 'target',hue = 'phase',data =df_metadata_train) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # https://www.w3resource.com/graphics/matplotlib/piechart/matplotlib-piechart-exercise-2.php | |
| data = df_metadata_train['phase'].value_counts() | |
| labels = ['Phase 0', 'Phase 1', 'Phase 3'] | |
| #colors = ["#1f77b4", "#ff7f0e", "#2ca02c"] | |
| title = 'Count of signals distributed by phase' | |
| plt.pie(data, labels=labels, shadow=True, startangle=90,autopct='%.1f%%') | |
| plt.title(title, bbox={'facecolor':'0.8', 'pad':5}) | |
| plt.show() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from sklearn.manifold import TSNE | |
| tsne = TSNE(n_components=2, perplexity=30, learning_rate=200, random_state=42) | |
| X_embedding = tsne.fit_transform(df_signal_train) | |
| y = np.array(df_signal_train['target']) | |
| tsne = np.hstack((X_embedding, y.reshape(-1,1))) | |
| tsne_to_df = pd.DataFrame(data=tsne, columns=['Dimension_x','Dimension_y','Score']) | |
| colors = {0:'red', 1:'blue', 2:'green'} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| fig=plt.figure(figsize=(14, 8), dpi= 120, facecolor='w', edgecolor='k') | |
| plot_labels = ['Phase_0', 'Phase_1', 'Phase_2'] | |
| plt.plot((df_signal_train.loc[0].values), label=plot_labels[0]) | |
| plt.plot((df_signal_train.loc[1].values), label=plot_labels[1]) | |
| plt.plot((df_signal_train.loc[2].values), label=plot_labels[2]) | |
| plt.ylim((-60, 60)) | |
| plt.legend(loc='lower right') | |
| plt.title('Raw Signal Data without Partial Discharge Fault') | |
| plt.xlabel('Sample') | |
| plt.ylabel('Amplitude [bit]') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def filtering(x, alpha=50, beta=1): | |
| x_new = np.zeros_like(x) | |
| zero = x[0] | |
| for i in range(1, len(x)): | |
| zero = zero*(alpha-beta)/alpha + beta*x[i]/alpha | |
| x_new[i] = x[i] - zero | |
| return x_new | |
| #Flattening a Normal signal | |
| normal_signal_filter = [None] * 3 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def standardize_data(signal, min_data, max_data, range_needed=(-1,1)): | |
| if min_data < 0: | |
| signal_std = (signal + abs(min_data)) / (max_data + abs(min_data)) | |
| else: | |
| signal_std = (signal - min_data) / (max_data - min_data) | |
| if range_needed[0] < 0: | |
| return signal_std * (range_needed[1] + abs(range_needed[0])) + range_needed[0] | |
| else: | |
| return signal_std * (range_needed[1] - range_needed[0]) + range_needed[0] |
OlderNewer