File size: 6,326 Bytes
3b66598
fff2149
3b66598
fff2149
4a389dc
66977cd
e8d4213
 
 
 
fff2149
3b66598
 
4a389dc
 
 
 
 
 
 
e8d4213
 
4a389dc
e8d4213
 
 
 
 
 
3b66598
 
e8d4213
3b66598
66977cd
3b66598
4a389dc
e8d4213
 
 
 
 
 
 
 
 
66977cd
3b66598
 
 
e8d4213
 
 
 
 
 
 
3b66598
4a389dc
3b66598
 
4a389dc
3b66598
e8d4213
 
 
 
 
 
 
 
 
66977cd
3b66598
4a389dc
e8d4213
 
 
 
 
 
 
 
 
 
4a389dc
3b66598
 
 
4a389dc
e8d4213
 
 
 
 
 
 
 
 
 
4a389dc
 
 
 
 
 
3b66598
 
4a389dc
e8d4213
 
 
 
 
 
 
 
 
 
 
3b66598
4a389dc
3b66598
fff2149
66977cd
e8d4213
 
 
 
 
 
 
 
 
 
 
 
 
 
66977cd
 
 
 
 
 
 
fff2149
4a389dc
e8d4213
 
 
 
 
 
 
 
 
3b66598
 
4a389dc
 
 
 
 
 
 
 
3b66598
fff2149
3b66598
e8d4213
 
 
 
 
 
 
 
 
 
 
66977cd
3b66598
 
 
 
4a389dc
66977cd
3b66598
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
import numpy as np
from tensorflow.keras.models import load_model
import joblib


class RTUAnomalizer2:
    """
    Class for performing anomaly detection on RTU (Roof Top Unit) data.
    """

    model = None
    kmeans_models = []

    def __init__(
        self,
        prediction_model_path=None,
        clustering_model_paths=None,
        num_inputs=None,
        num_outputs=None,
    ):
        """
        Initialize the RTUAnomalizer object.

        Args:
            prediction_model_path (str): Path to the prediction model file.
            clustering_model_paths (list): List of paths to the clustering model files.
            num_inputs (int): Number of input features.
            num_outputs (int): Number of output features.
        """
        self.num_inputs = num_inputs
        self.num_outputs = num_outputs
        if prediction_model_path is not None and clustering_model_paths is not None:
            self.load_models(prediction_model_path, clustering_model_paths)
        self.actual_list, self.pred_list, self.resid_list = self.initialize_lists()

    def initialize_lists(self, size=30):
        """
        Initialize lists for storing actual, predicted, and residual values.

        Args:
            size (int): Size of the lists.

        Returns:
            tuple: A tuple containing three lists initialized with zeros.
        """
        initial_values = [[0]*self.num_outputs] * size
        return initial_values.copy(), initial_values.copy(), initial_values.copy()

    def load_models(self, prediction_model_path, clustering_model_paths):
        """
        Load the prediction and clustering models.

        Args:
            prediction_model_path (str): Path to the prediction model file.
            clustering_model_paths (list): List of paths to the clustering model files.
        """
        self.model = load_model(prediction_model_path)

        for path in clustering_model_paths:
            self.kmeans_models.append(joblib.load(path))

    def predict(self, df_new):
        """
        Make predictions using the prediction model.

        Args:
            df_new (DataFrame): Input data for prediction.

        Returns:
            array: Predicted values.
        """
        return self.model.predict(df_new,verbose=0)

    def calculate_residuals(self, df_trans, pred):
        """
        Calculate the residuals between actual and predicted values.

        Args:
            df_trans (DataFrame): Transformed input data.
            pred (array): Predicted values.

        Returns:
            tuple: A tuple containing the actual values and residuals.
        """
        actual = df_trans[30, : self.num_outputs]
        resid = actual - pred
        return actual, resid

    def resize_prediction(self, pred, df_trans):
        """
        Resize the predicted values to match the shape of the transformed input data.

        Args:
            pred (array): Predicted values.
            df_trans (DataFrame): Transformed input data.

        Returns:
            array: Resized predicted values.
        """
        pred = np.resize(
            pred, (pred.shape[0], pred.shape[1] + len(df_trans[30, self.num_outputs :]))
        )
        pred[:, -len(df_trans[30, self.num_outputs :]) :] = df_trans[
            30, self.num_outputs :
        ]
        return pred

    def inverse_transform(self, scaler, pred, df_trans):
        """
        Inverse transform the predicted and actual values.

        Args:
            scaler (object): Scaler object for inverse transformation.
            pred (array): Predicted values.
            df_trans (DataFrame): Transformed input data.

        Returns:
            tuple: A tuple containing the actual and predicted values after inverse transformation.
        """
        pred = scaler.inverse_transform(np.array(pred))
        actual = scaler.inverse_transform(np.array([df_trans[30, :]]))
        return actual, pred

    def update_lists(self, actual, pred, resid):
        """
        Update the lists of actual, predicted, and residual values.

        Args:
            actual_list (list): List of actual values.
            pred_list (list): List of predicted values.
            resid_list (list): List of residual values.
            actual (array): Actual values.
            pred (array): Predicted values.
            resid (array): Residual values.

        Returns:
            tuple: A tuple containing the updated lists of actual, predicted, and residual values.
        """
        self.actual_list.pop(0)
        self.pred_list.pop(0)
        self.resid_list.pop(0)
        self.actual_list.append(actual.flatten().tolist())
        self.pred_list.append(pred.flatten().tolist())
        self.resid_list.append(resid.flatten().tolist())
        return self.actual_list, self.pred_list, self.resid_list

    def calculate_distances(self, resid):
        """
        Calculate the distances between residuals and cluster centers.

        Args:
            resid (array): Residual values.

        Returns:
            array: Array of distances.
        """
        dist = []
        for i, model in enumerate(self.kmeans_models):
            dist.append(
                np.linalg.norm(
                    resid[:, (i * 7) + 1 : (i * 7) + 8] - model.cluster_centers_[0],
                    ord=2,
                    axis=1,
                )
            )

        return np.array(dist)

    def pipeline(self, df_new, df_trans, scaler):
        """
        Perform the anomaly detection pipeline.

        Args:
            df_new (DataFrame): Input data for prediction.
            df_trans (DataFrame): Transformed input data.
            scaler (object): Scaler object for inverse transformation.

        Returns:
            tuple: A tuple containing the lists of actual, predicted, and residual values, and the distances.
        """
        
        pred = self.predict(df_new)
        actual, resid = self.calculate_residuals(df_trans, pred)
        pred = self.resize_prediction(pred, df_trans)
        actual, pred = self.inverse_transform(scaler, pred, df_trans)
        actual_list, pred_list, resid_list = self.update_lists(
             actual, pred, resid)
        dist = self.calculate_distances(resid)
        return actual_list, pred_list, resid_list, dist