sarapy 3.0.0__tar.gz → 3.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (43) hide show
  1. {sarapy-3.0.0/sarapy.egg-info → sarapy-3.1.1}/PKG-INFO +35 -12
  2. {sarapy-3.0.0 → sarapy-3.1.1}/README.md +10 -0
  3. sarapy-3.1.1/pyproject.toml +47 -0
  4. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/dataProcessing/OpsProcessor.py +4 -3
  5. sarapy-3.1.1/sarapy/mlProcessors/FertilizerTransformer.py +198 -0
  6. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/version.py +1 -1
  7. {sarapy-3.0.0 → sarapy-3.1.1/sarapy.egg-info}/PKG-INFO +35 -12
  8. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy.egg-info/SOURCES.txt +4 -1
  9. sarapy-3.1.1/sarapy.egg-info/requires.txt +15 -0
  10. sarapy-3.1.1/sarapy.egg-info/top_level.txt +5 -0
  11. sarapy-3.1.1/setup.py +40 -0
  12. sarapy-3.1.1/test/checking_regresor.py +162 -0
  13. sarapy-3.1.1/test/probabilidades_test.py +77 -0
  14. sarapy-3.1.1/test/test_import.py +5 -0
  15. sarapy-3.0.0/pyproject.toml +0 -21
  16. sarapy-3.0.0/sarapy/mlProcessors/FertilizerTransformer.py +0 -70
  17. sarapy-3.0.0/sarapy.egg-info/requires.txt +0 -6
  18. sarapy-3.0.0/sarapy.egg-info/top_level.txt +0 -1
  19. sarapy-3.0.0/setup.py +0 -35
  20. {sarapy-3.0.0 → sarapy-3.1.1}/LICENCE +0 -0
  21. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/__init__.py +0 -0
  22. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/analysis/FeaturesResume.py +0 -0
  23. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/analysis/__init__.py +0 -0
  24. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/dataProcessing/GeoProcessor.py +0 -0
  25. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/dataProcessing/TLMSensorDataProcessor.py +0 -0
  26. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/dataProcessing/TimeSeriesProcessor.py +0 -0
  27. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/dataProcessing/__init__.py +0 -0
  28. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/mlProcessors/FertilizerFMCreator.py +0 -0
  29. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/mlProcessors/PlantinClassifier.py +0 -0
  30. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/mlProcessors/PlantinFMCreator.py +0 -0
  31. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/mlProcessors/__init__.py +0 -0
  32. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/preprocessing/DistancesImputer.py +0 -0
  33. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/preprocessing/FertilizerImputer.py +0 -0
  34. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/preprocessing/TransformInputData.py +0 -0
  35. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/preprocessing/TransformToOutputData.py +0 -0
  36. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/preprocessing/__init__.py +0 -0
  37. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/stats/__init__.py +0 -0
  38. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/stats/stats.py +0 -0
  39. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/utils/__init__.py +0 -0
  40. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/utils/plotting.py +0 -0
  41. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy/utils/utils.py +0 -0
  42. {sarapy-3.0.0 → sarapy-3.1.1}/sarapy.egg-info/dependency_links.txt +0 -0
  43. {sarapy-3.0.0 → sarapy-3.1.1}/setup.cfg +0 -0
@@ -1,24 +1,47 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.4
2
2
  Name: sarapy
3
- Version: 3.0.0
4
- Home-page: https://github.com/lucasbaldezzari/sarapy
5
- Author: Lucas Baldezzari
3
+ Version: 3.1.1
4
+ Summary: Library for Sarapico Metadata processing
6
5
  Author-email: Lucas Baldezzari <lmbaldezzari@gmail.com>
7
- Maintainer-email: Lucas Baldezzari <lmbaldezzari@gmail.com>
8
- License: For private use only. Owner AMG Servicios profesionales (Mercedes, Uruguay)
6
+ License: MIT
7
+ Classifier: License :: OSI Approved :: MIT License
8
+ Classifier: Programming Language :: Python :: 3
9
+ Classifier: Operating System :: Microsoft :: Windows :: Windows 10
10
+ Classifier: Operating System :: Microsoft :: Windows :: Windows 11
11
+ Classifier: Operating System :: Unix
12
+ Requires-Python: >=3.9
9
13
  Description-Content-Type: text/markdown
10
14
  License-File: LICENCE
11
- Requires-Dist: numpy
12
- Requires-Dist: matplotlib
13
- Requires-Dist: pandas
14
- Requires-Dist: scipy
15
- Requires-Dist: scikit-learn
16
- Requires-Dist: geopy
15
+ Requires-Dist: numpy>=1.23
16
+ Requires-Dist: pandas>=1.5
17
+ Requires-Dist: scipy>=1.9
18
+ Requires-Dist: scikit-learn>=1.2
19
+ Requires-Dist: matplotlib>=3.6
20
+ Requires-Dist: seaborn>=0.12
21
+ Requires-Dist: requests>=2.28
22
+ Requires-Dist: python-dotenv>=1.0
23
+ Requires-Dist: geopy>=2.3
24
+ Provides-Extra: dev
25
+ Requires-Dist: pytest; extra == "dev"
26
+ Requires-Dist: black; extra == "dev"
27
+ Requires-Dist: ruff; extra == "dev"
28
+ Requires-Dist: mypy; extra == "dev"
29
+ Dynamic: license-file
17
30
 
18
31
  # SARAPY
19
32
 
20
33
  Library for processing SARAPICO project metadata of _AMG SA_.
21
34
 
35
+ #### Version 3.1.1
36
+
37
+ - Se vuelve a generar archivos de regresor_v2 y poly_features_v2 porque quedó mal cargado.
38
+
39
+ #### Version 3.1.0
40
+
41
+ - Se actualiza regresor para estimar fertilizante.
42
+ - Actualización de archivos para instalar la libería.
43
+
44
+
22
45
  #### Version 3.0.0
23
46
  - Se mejora la forma de obtener valores de media movil para todas las variables en las que se usa.
24
47
  - Se corrigen bugs debido a nodos con pocas operaciones.
@@ -2,6 +2,16 @@
2
2
 
3
3
  Library for processing SARAPICO project metadata of _AMG SA_.
4
4
 
5
+ #### Version 3.1.1
6
+
7
+ - Se vuelve a generar archivos de regresor_v2 y poly_features_v2 porque quedó mal cargado.
8
+
9
+ #### Version 3.1.0
10
+
11
+ - Se actualiza regresor para estimar fertilizante.
12
+ - Actualización de archivos para instalar la libería.
13
+
14
+
5
15
  #### Version 3.0.0
6
16
  - Se mejora la forma de obtener valores de media movil para todas las variables en las que se usa.
7
17
  - Se corrigen bugs debido a nodos con pocas operaciones.
@@ -0,0 +1,47 @@
1
+ [build-system]
2
+ requires = ["setuptools>=64", "wheel"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "sarapy"
7
+ version = "3.1.1"
8
+ description = "Library for Sarapico Metadata processing"
9
+ readme = "README.md"
10
+ requires-python = ">=3.9"
11
+
12
+ authors = [
13
+ { name = "Lucas Baldezzari", email = "lmbaldezzari@gmail.com" }
14
+ ]
15
+
16
+ license = { text = "MIT" }
17
+
18
+ classifiers = [
19
+ "License :: OSI Approved :: MIT License",
20
+ "Programming Language :: Python :: 3",
21
+ "Operating System :: Microsoft :: Windows :: Windows 10",
22
+ "Operating System :: Microsoft :: Windows :: Windows 11",
23
+ "Operating System :: Unix",
24
+ ]
25
+
26
+ dependencies = [
27
+ "numpy>=1.23",
28
+ "pandas>=1.5",
29
+ "scipy>=1.9",
30
+ "scikit-learn>=1.2",
31
+ "matplotlib>=3.6",
32
+ "seaborn>=0.12",
33
+ "requests>=2.28",
34
+ "python-dotenv>=1.0",
35
+ "geopy>=2.3",
36
+ ]
37
+
38
+ [project.optional-dependencies]
39
+ dev = [
40
+ "pytest",
41
+ "black",
42
+ "ruff",
43
+ "mypy",
44
+ ]
45
+
46
+ [tool.setuptools]
47
+ packages = { find = {} }
@@ -32,8 +32,8 @@ class OpsProcessor():
32
32
  self.classifications_probas = None
33
33
  plclass_map = {"classifier_file"}
34
34
  self._operationsDict = {} ##diccionario de operarios con sus operaciones
35
- self._platin_classifiedOperations = np.array([]) ##array con las operaciones clasificadas para plantin
36
- self._fertilizer_classifiedOperations = np.array([]) ##array con las operaciones clasificadas para plantin
35
+ # self._platin_classifiedOperations = np.array([]) ##array con las operaciones clasificadas para plantin
36
+ # self._fertilizer_classifiedOperations = np.array([]) ##array con las operaciones clasificadas para plantin
37
37
  self._last_row_db = 0 ##indicador de la última fila de los datos extraidos de la base de datos histórica
38
38
 
39
39
  kwargs_plclass = {}
@@ -343,7 +343,8 @@ if __name__ == "__main__":
343
343
  samples = json.load(file)
344
344
 
345
345
  op = OpsProcessor(classifier_file='modelos\\pipeline_rf.pkl',
346
- regresor_file='modelos\\regresor.pkl', poly_features_file='modelos\\poly_features.pkl',
346
+ # regresor_file='modelos\\regresor.pkl', poly_features_file='modelos\\poly_features.pkl',
347
+ regresor_file='modelos\\regresor_v2.pkl', poly_features_file='modelos\\poly_features_v2.pkl',
347
348
  **kwargs_fmcreator)
348
349
 
349
350
  ops_clasificadas = op.processOperations(samples, **kwargs_classifier)
@@ -0,0 +1,198 @@
1
+ import pickle
2
+ import logging
3
+ from sarapy.dataProcessing import TLMSensorDataProcessor
4
+
5
+ class FertilizerTransformer:
6
+ """
7
+ Clase para tomar los valores de distorsión de fertilizante y transformarlos a gramos
8
+ """
9
+
10
+ def __init__(self, regresor_file, poly_features_file):
11
+ """Constructor de la clase FertilizerImputer.
12
+
13
+ Args:
14
+ - regresor: Regresor que transforma los valores de distorsión a gramos.
15
+ - poly_features: Grado del polinomio a utilizar en la transformación de los datos.
16
+ """
17
+ self.logger = logging.getLogger("FertilizerTransformer")
18
+ ##cargo el regresor con pickle. Usamos try para capturar el error FileNotFoundError
19
+ try:
20
+ with open(regresor_file, 'rb') as file:
21
+ self._regresor = pickle.load(file)
22
+ self.logger.info("Regresor cargado con éxito.")
23
+ except FileNotFoundError:
24
+ self.logger.error("El archivo no se encuentra en el directorio actual.")
25
+
26
+ ##cargo las características polinómicas con pickle. Usamos try para capturar el error FileNotFoundError
27
+ try:
28
+ with open(poly_features_file, 'rb') as file:
29
+ self._poly_features = pickle.load(file)
30
+ self.logger.info("Características polinómicas cargadas con éxito.")
31
+ except FileNotFoundError:
32
+ self.logger.error("El archivo no se encuentra en el directorio actual.")
33
+
34
+ self.fertilizer_grams = None ##cuando no se ha transformado ningún dato, se inicializa en None
35
+
36
+
37
+ def transform(self, data):
38
+ """Transforma los datos de distorsión de fertilizante a gramos.
39
+
40
+ Params:
41
+ - data: Es una lista de diccionarios (como un JSON) con los datos de telemetría.
42
+
43
+ Returns:
44
+ - 0: Array con los valores de distorsión de fertilizante transformados a gramos.
45
+ """
46
+ tlmDataProcessor = TLMSensorDataProcessor.TLMSensorDataProcessor(data)
47
+ X = tlmDataProcessor["SC_FT",:]
48
+ X_poly = self._poly_features.fit_transform(X.reshape(-1, 1))
49
+ self.fertilizer_grams = self._regresor.predict(X_poly)
50
+
51
+ ##para valores de distorsión de 13+-0.3 y 15+-0.3, pongo los valores en 8 y 9 gramos, respectivamente
52
+ ##uso máscara booleana para encontrar los índices
53
+ mask_13 = (X >= 12.7) & (X <= 13.3)
54
+ mask_15 = (X >= 14.7) & (X <= 15.3)
55
+ self.fertilizer_grams[mask_13] = 8
56
+ self.fertilizer_grams[mask_15] = 9
57
+
58
+ ##retorno con shape (n,)
59
+ return self.fertilizer_grams.reshape(-1,)
60
+
61
+ if __name__ == "__main__":
62
+ import pandas as pd
63
+ import numpy as np
64
+ import json
65
+ from sarapy.preprocessing import TransformInputData
66
+ import matplotlib.pyplot as plt
67
+ from collections import Counter
68
+
69
+ fecha = "2025-08-09"
70
+ nodo_interes = "UPM095N"
71
+
72
+ historical_data_path = f"examples//{fecha}//{nodo_interes}//historical-data.json"
73
+ with open(historical_data_path, 'r') as file:
74
+ historical_data = json.load(file)
75
+
76
+ ##cargo en un diccionario sarapy\preprocessing\telemetriaDataPosition.json
77
+ data_positions = json.load(open("sarapy/preprocessing/telemetriaDataPosition.json", 'r'))
78
+ transform_input_data = TransformInputData()
79
+ transformed_data = transform_input_data.transform(historical_data)
80
+
81
+ fertransformer = FertilizerTransformer(regresor_file='modelos\\regresor_v2.pkl', poly_features_file='modelos\\poly_features_v2.pkl')
82
+ gramos = fertransformer.transform(transformed_data)
83
+ print(gramos[:10])
84
+
85
+ df = pd.DataFrame(transformed_data)
86
+ score_ft = df["SC_FT"].values
87
+
88
+ print(score_ft.mean(), gramos.mean())
89
+ print(score_ft.max(), gramos.max())
90
+ print(score_ft.min(), gramos.min())
91
+
92
+ puntos = list(zip(score_ft, gramos))
93
+ conteos = Counter(puntos)
94
+ xs, ys, sizes = zip(*[(x, y, c) for (x, y), c in conteos.items()])
95
+
96
+ np.array([s*10 for s in sizes]).shape
97
+
98
+ points = np.column_stack((score_ft, gramos))
99
+ unique_points, counts = np.unique(points, axis=0, return_counts=True)
100
+
101
+ sizes = np.log1p(counts) * 50
102
+
103
+ plt.figure(figsize=(10, 6))
104
+ handles, labels = plt.gca().get_legend_handles_labels()
105
+ order = [2, 0, 1]
106
+ plt.scatter(unique_points[:,0], unique_points[:,1], color="#5612af", label="Regresor 1 - Orden 12",zorder=1,
107
+ s=sizes)
108
+ plt.scatter(score_ft.mean(), gramos.mean(), color="#af121f", label="Punto promedio", marker='X',s=400)
109
+ plt.title(f'Predicciones Regresor 2 de orden 12 para NODO: {nodo_interes}')
110
+ plt.xlabel('Score de Fertilizante (SC_FT)')
111
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
112
+ plt.grid(True)
113
+ plt.legend()
114
+ plt.savefig(f'predicciones_regresor2_orden12_{nodo_interes}.png')
115
+ plt.show()
116
+
117
+ nodos = ["UPM075N", "UPM076N", "UPM077N", "UPM078N", "UPM079N", "UPM080N", "UPM081N", "UPM082N", "UPM083N", "UPM084N",
118
+ "UPM085N", "UPM086N", "UPM087N", "UPM088N", "UPM089N", "UPM090N", "UPM091N", "UPM092N", "UPM093N", "UPM094N", "UPM095N",
119
+ "UPM096N", "UPM097N", "UPM098N", "UPM099N"]
120
+
121
+ ##cargo datos históricos de ejemplo
122
+
123
+ scores_ft_maximos = {}
124
+ scores_ft_minimos = {}
125
+ gramos_maximos = {}
126
+ gramos_minimos = {}
127
+ for nodo in nodos:
128
+ historical_data_path = f"examples//{fecha}//{nodo}//historical-data.json"
129
+ try:
130
+ with open(historical_data_path, 'r') as file:
131
+ historical_data = json.load(file)
132
+ except FileNotFoundError:
133
+ print(f"El archivo {historical_data_path} no se encuentra en el directorio actual.")
134
+ continue
135
+ transform_input_data = TransformInputData()
136
+ transformed_data = transform_input_data.transform(historical_data)
137
+ fertransformer = FertilizerTransformer(regresor_file='modelos\\regresor_v2.pkl', poly_features_file='modelos\\poly_features_v2.pkl')
138
+ gramos = fertransformer.transform(transformed_data)
139
+ gramos_maximos[nodo] = gramos.max()
140
+ gramos_minimos[nodo] = gramos.min()
141
+
142
+ df = pd.DataFrame(transformed_data)
143
+ score_ft = df["SC_FT"].values
144
+ scores_ft_maximos[nodo] = score_ft.max()
145
+ scores_ft_minimos[nodo] = score_ft.min()
146
+
147
+ data = np.array([[gramos_maximos[nodo] for nodo in nodos],
148
+ [scores_ft_maximos[nodo] for nodo in nodos],
149
+ [gramos_minimos[nodo] for nodo in nodos],
150
+ [scores_ft_minimos[nodo] for nodo in nodos]])
151
+
152
+ data_df = pd.DataFrame(data=data.T, index=nodos, columns=['Gramos_Fertilizante', 'Score_Fertilizante', 'Gramos_Fertilizante_Min', 'Score_Fertilizante_Min'])
153
+
154
+ data_df['Gramos_Fertilizante'].plot.bar(figsize=(12, 6), color="#34a853", legend=False)
155
+ #add text labels on top of each bar with the height value
156
+ for i, v in enumerate(data_df['Gramos_Fertilizante']):
157
+ plt.text(i, v + 0.1, f"{v:.1f}", ha='center', va='bottom',color="#34a853")
158
+ plt.title('Máximos de gramos de fertilizante por nodo')
159
+ plt.xlabel('Nodos')
160
+ plt.ylabel('Gramos de Fertilizante')
161
+ plt.grid(axis='y')
162
+ plt.savefig('maximos_gramos_fertilizante_por_nodo.png')
163
+ plt.show()
164
+
165
+ data_df['Gramos_Fertilizante_Min'].plot.bar(figsize=(12, 6), color="#34a853", legend=False)
166
+ #add text labels on top of each bar with the height value
167
+ for i, v in enumerate(data_df['Gramos_Fertilizante_Min']):
168
+ plt.text(i, v + 0.1, f"{v:.1f}", ha='center', va='bottom',color="#34a853")
169
+ plt.title('Mínimos de gramos de fertilizante por nodo')
170
+ plt.xlabel('Nodos')
171
+ plt.ylabel('Gramos de Fertilizante')
172
+ plt.grid(axis='y')
173
+ plt.savefig('minimos_gramos_fertilizante_por_nodo.png')
174
+ plt.show()
175
+
176
+ data_df['Score_Fertilizante'].plot.bar(figsize=(12, 6), color="#3434a8", legend=False)
177
+ #add text labels on top of each bar with the height value
178
+ for i, v in enumerate(data_df['Score_Fertilizante']):
179
+ plt.text(i, v + 0.1, f"{v:.1f}", ha='center', va='bottom',color="#3434a8")
180
+ plt.title('Máximos de score de fertilizante por nodo')
181
+ plt.xlabel('Nodos')
182
+ plt.ylabel('Score de Fertilizante')
183
+ plt.grid(axis='y')
184
+ plt.savefig('maximos_score_fertilizante_por_nodo.png')
185
+ plt.show()
186
+
187
+ data_df['Score_Fertilizante_Min'].plot.bar(figsize=(12, 6), color="#3434a8", legend=False)
188
+ #add text labels on top of each bar with the height value
189
+ for i, v in enumerate(data_df['Score_Fertilizante_Min']):
190
+ plt.text(i, v + 0.1, f"{v:.1f}", ha='center', va='bottom',color="#3434a8")
191
+ plt.title('Mínimos de score de fertilizante por nodo')
192
+ plt.xlabel('Nodos')
193
+ plt.ylabel('Score de Fertilizante')
194
+ plt.grid(axis='y')
195
+ plt.savefig('minimos_score_fertilizante_por_nodo.png')
196
+ plt.show()
197
+
198
+
@@ -1,2 +1,2 @@
1
1
  ## Version of the package
2
- __version__ = "3.0.0"
2
+ __version__ = "3.1.1"
@@ -1,24 +1,47 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.4
2
2
  Name: sarapy
3
- Version: 3.0.0
4
- Home-page: https://github.com/lucasbaldezzari/sarapy
5
- Author: Lucas Baldezzari
3
+ Version: 3.1.1
4
+ Summary: Library for Sarapico Metadata processing
6
5
  Author-email: Lucas Baldezzari <lmbaldezzari@gmail.com>
7
- Maintainer-email: Lucas Baldezzari <lmbaldezzari@gmail.com>
8
- License: For private use only. Owner AMG Servicios profesionales (Mercedes, Uruguay)
6
+ License: MIT
7
+ Classifier: License :: OSI Approved :: MIT License
8
+ Classifier: Programming Language :: Python :: 3
9
+ Classifier: Operating System :: Microsoft :: Windows :: Windows 10
10
+ Classifier: Operating System :: Microsoft :: Windows :: Windows 11
11
+ Classifier: Operating System :: Unix
12
+ Requires-Python: >=3.9
9
13
  Description-Content-Type: text/markdown
10
14
  License-File: LICENCE
11
- Requires-Dist: numpy
12
- Requires-Dist: matplotlib
13
- Requires-Dist: pandas
14
- Requires-Dist: scipy
15
- Requires-Dist: scikit-learn
16
- Requires-Dist: geopy
15
+ Requires-Dist: numpy>=1.23
16
+ Requires-Dist: pandas>=1.5
17
+ Requires-Dist: scipy>=1.9
18
+ Requires-Dist: scikit-learn>=1.2
19
+ Requires-Dist: matplotlib>=3.6
20
+ Requires-Dist: seaborn>=0.12
21
+ Requires-Dist: requests>=2.28
22
+ Requires-Dist: python-dotenv>=1.0
23
+ Requires-Dist: geopy>=2.3
24
+ Provides-Extra: dev
25
+ Requires-Dist: pytest; extra == "dev"
26
+ Requires-Dist: black; extra == "dev"
27
+ Requires-Dist: ruff; extra == "dev"
28
+ Requires-Dist: mypy; extra == "dev"
29
+ Dynamic: license-file
17
30
 
18
31
  # SARAPY
19
32
 
20
33
  Library for processing SARAPICO project metadata of _AMG SA_.
21
34
 
35
+ #### Version 3.1.1
36
+
37
+ - Se vuelve a generar archivos de regresor_v2 y poly_features_v2 porque quedó mal cargado.
38
+
39
+ #### Version 3.1.0
40
+
41
+ - Se actualiza regresor para estimar fertilizante.
42
+ - Actualización de archivos para instalar la libería.
43
+
44
+
22
45
  #### Version 3.0.0
23
46
  - Se mejora la forma de obtener valores de media movil para todas las variables en las que se usa.
24
47
  - Se corrigen bugs debido a nodos con pocas operaciones.
@@ -30,4 +30,7 @@ sarapy/stats/__init__.py
30
30
  sarapy/stats/stats.py
31
31
  sarapy/utils/__init__.py
32
32
  sarapy/utils/plotting.py
33
- sarapy/utils/utils.py
33
+ sarapy/utils/utils.py
34
+ test/checking_regresor.py
35
+ test/probabilidades_test.py
36
+ test/test_import.py
@@ -0,0 +1,15 @@
1
+ numpy>=1.23
2
+ pandas>=1.5
3
+ scipy>=1.9
4
+ scikit-learn>=1.2
5
+ matplotlib>=3.6
6
+ seaborn>=0.12
7
+ requests>=2.28
8
+ python-dotenv>=1.0
9
+ geopy>=2.3
10
+
11
+ [dev]
12
+ pytest
13
+ black
14
+ ruff
15
+ mypy
@@ -0,0 +1,5 @@
1
+ docs
2
+ examples
3
+ modelos
4
+ sarapy
5
+ test
sarapy-3.1.1/setup.py ADDED
@@ -0,0 +1,40 @@
1
+ #from setuptools import setup#, find_packages
2
+
3
+ from setuptools import setup
4
+
5
+ setup()
6
+
7
+ # import toml
8
+
9
+ # def getRequirements():
10
+ # with open('requirements.txt', 'r') as f:
11
+ # requirements = f.read().splitlines()
12
+ # return requirements
13
+
14
+ # def readme():
15
+ # with open('README.md') as f:
16
+ # return f.read()
17
+
18
+ # def version():
19
+ # with open('pyproject.toml') as f:
20
+ # return toml.load(f)['project']['version']
21
+
22
+ # setup(
23
+ # name='sarapy',
24
+ # version=version(),
25
+ # packages=find_packages(),
26
+ # install_requires=getRequirements(),
27
+ # author='Lucas Baldezzari',
28
+ # author_email='lmbaldezzari@gmail.com',
29
+ # description='Library for Sarapico Metadata processing',
30
+ # long_description=readme(),
31
+ # url='https://github.com/lucasbaldezzari/sarapy',
32
+ # license='MIT', ##revisar licencia
33
+ # classifiers=[
34
+ # 'License :: OSI Approved :: MIT License',
35
+ # 'Programming Language :: Python :: 3',
36
+ # 'Operating System :: Microsoft :: Windows :: Windows 10',
37
+ # 'Operating System :: Microsoft :: Windows :: Windows 11',
38
+ # 'Operating System :: Unix',
39
+ # ],
40
+ # )
@@ -0,0 +1,162 @@
1
+ import pickle
2
+ import pandas as pd
3
+ import numpy as np
4
+ import matplotlib.pyplot as plt
5
+ from sklearn.preprocessing import PolynomialFeatures
6
+ from sklearn.linear_model import LinearRegression
7
+ from sklearn.preprocessing import StandardScaler
8
+
9
+ regresor = "modelos//regresor.pkl"
10
+ poly_features = "modelos//poly_features.pkl"
11
+
12
+ with open(regresor, "rb") as file:
13
+ loaded_regresor = pickle.load(file)
14
+
15
+ with open(poly_features, "rb") as file:
16
+ loaded_poly_features = pickle.load(file)
17
+
18
+ coeficientes = loaded_regresor.coef_.flatten()
19
+ intercept = loaded_regresor.intercept_
20
+ index = np.arange(len(coeficientes)) + 1
21
+ distorsiones = np.linspace(0, 15, 1000)
22
+ X_poly = loaded_poly_features.transform(distorsiones.reshape(-1, 1))
23
+ predicciones = loaded_regresor.predict(X_poly)
24
+
25
+ ##genero un dataframe con los coeficientes
26
+ labels = [f"Exponente/Coeficiente {i}" for i in index]
27
+ tabla = pd.DataFrame(coeficientes, labels).rename(columns={0:"Valores"})
28
+ tabla.loc[len(tabla)+1] = intercept
29
+ tabla = tabla.rename(index={len(tabla):"intercepción"})
30
+
31
+ #grafico de líneas de los coeficientes vs su índice
32
+ plt.figure(figsize=(10, 6))
33
+ plt.plot(index, coeficientes, marker='o', linestyle='-', color='b')
34
+ plt.title('Coeficientes del Regresor Polinómico')
35
+ plt.xlabel('Índice del Coeficiente')
36
+ plt.ylabel('Valor del Coeficiente')
37
+ plt.grid(True)
38
+ plt.axhline(0, color='black', linewidth=0.8, linestyle='--')
39
+ plt.show()
40
+
41
+ # gráfico de dispersión de distorsión vs predicciones
42
+ plt.figure(figsize=(10, 6))
43
+ plt.scatter(distorsiones, predicciones, color='r', alpha=0.6)
44
+ plt.title('Score de Fertilizante vs Predicciones en Gramos')
45
+ plt.xlabel('Score de Fertilizante (SC_FT)')
46
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
47
+ plt.grid(True)
48
+ plt.show()
49
+
50
+ inf, sup = 7, 13
51
+ distorsiones[int(inf/0.1):int(sup/0.1+1)].mean()
52
+ predicciones[int(inf/0.1):int(sup/0.1+1)].mean()
53
+
54
+
55
+ # Definición de tramos: (x1, x2, y1, y2)
56
+ segmentos1 = [(0, 4, 0, 0.821),
57
+ (4, 7, 0.821, 5),
58
+ (7, 9.5, 5, 5.41),
59
+ (9.5, 13, 5.41, 8),
60
+ (13, 15, 8, 9)]
61
+ segmentos2 = [(0, 4, 0, 0.821),
62
+ (4, 7, 0.821, 5),
63
+ # (7, 9.5, 5, 5.41),
64
+ (7, 13, 5, 8),
65
+ (13, 15, 8, 9)]
66
+
67
+ def get_line(x1, x2, y1, y2):
68
+ m = (y2 - y1) / (x2 - x1)
69
+ b = y1 - m * x1
70
+ return m, b
71
+
72
+ def piecewise_linear(x, segmentos, lines):
73
+ for (x1, x2, _, _), (m, b) in zip(segmentos, lines):
74
+ if x1 <= x <= x2:
75
+ return m * x + b
76
+ raise ValueError("x fuera de rango")
77
+
78
+ lines1 = [get_line(*seg) for seg in segmentos1]
79
+ lines2 = [get_line(*seg) for seg in segmentos2]
80
+
81
+ # Ejemplo
82
+ ys1 = np.array([piecewise_linear(x, segmentos1, lines1) for x in distorsiones])
83
+ ys2 = np.array([piecewise_linear(x, segmentos2, lines2) for x in distorsiones])
84
+
85
+ # gráfico de dispersión de distorsión vs predicciones
86
+ plt.figure(figsize=(10, 6))
87
+ handles, labels = plt.gca().get_legend_handles_labels()
88
+ order = [2, 0, 1]
89
+ plt.scatter(distorsiones, predicciones, color='r', alpha=0.5, label="Predicciones actuales",zorder=2)
90
+ plt.scatter(distorsiones, ys1, color='g', alpha=0.5, label="Propuesta 1",zorder=1)
91
+ plt.scatter(distorsiones, ys2, color='b', alpha=0.5, label="Propuesta 2",zorder=0)
92
+ plt.title('Score de Fertilizante vs Predicciones en Gramos')
93
+ plt.xlabel('Score de Fertilizante (SC_FT)')
94
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
95
+ plt.grid(True)
96
+ plt.legend()
97
+ plt.show()
98
+
99
+
100
+ ### ************* Obteniendo nuevos regresores a partir de ys1 y ys2 ************* ###
101
+ X = distorsiones.reshape(-1, 1)
102
+
103
+ poly = PolynomialFeatures(
104
+ degree=12,
105
+ include_bias=True # incluye el término β0
106
+ )
107
+
108
+ X_poly = poly.fit_transform(X)
109
+
110
+ modelo1 = LinearRegression(fit_intercept=False)
111
+ modelo1.fit(X_poly, ys1)
112
+ modelo2 = LinearRegression(fit_intercept=False)
113
+ modelo2.fit(X_poly, ys2)
114
+
115
+ ys1_pred = modelo1.predict(X_poly)
116
+ ys2_pred = modelo2.predict(X_poly)
117
+
118
+ # gráfico de dispersión de distorsión vs predicciones
119
+ plt.figure(figsize=(10, 6))
120
+ handles, labels = plt.gca().get_legend_handles_labels()
121
+ order = [2, 0, 1]
122
+ plt.scatter(distorsiones, ys1, color='g', alpha=0.1, label="Función 1 Hardcodeada ",zorder=1)
123
+ plt.scatter(distorsiones, ys1_pred, color="#5612af", alpha=0.5, label="Regresor 1 - Orden 12",zorder=2)
124
+ plt.title('Comparación Función de Propuesta vs Regresor 1 de orden 12')
125
+ plt.xlabel('Score de Fertilizante (SC_FT)')
126
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
127
+ plt.grid(True)
128
+ plt.legend()
129
+ plt.show()
130
+
131
+ # gráfico de dispersión de distorsión vs predicciones
132
+ plt.figure(figsize=(10, 6))
133
+ handles, labels = plt.gca().get_legend_handles_labels()
134
+ order = [2, 0, 1]
135
+ plt.scatter(distorsiones, ys2, color='b', alpha=0.1, label="Función 2 Hardcodeada ",zorder=1)
136
+ plt.scatter(distorsiones, ys2_pred, color="#12af12", alpha=0.5, label="Regresor 2 - Orden 12",zorder=2)
137
+ plt.title('Comparación Función de Propuesta vs Regresor 2 de orden 12')
138
+ plt.xlabel('Score de Fertilizante (SC_FT)')
139
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
140
+ plt.grid(True)
141
+ plt.legend()
142
+ plt.show()
143
+
144
+ # gráfico de dispersión de distorsión vs predicciones
145
+ plt.figure(figsize=(10, 6))
146
+ handles, labels = plt.gca().get_legend_handles_labels()
147
+ order = [2, 0, 1]
148
+ plt.scatter(distorsiones, ys1_pred, color="#5612af", alpha=0.1, label="Regresor 1 - Orden 12",zorder=1)
149
+ plt.scatter(distorsiones, ys2_pred, color="#12af12", alpha=0.5, label="Regresor 2 - Orden 12",zorder=2)
150
+ plt.title('Regresor 1 vs Regresor 2 de orden 12')
151
+ plt.xlabel('Score de Fertilizante (SC_FT)')
152
+ plt.ylabel('Predicciones de Gramos de Fertilizante')
153
+ plt.grid(True)
154
+ plt.legend()
155
+ plt.show()
156
+
157
+ ## Guardo el modelo 2 y las características polinómicas
158
+ with open("modelos//regresor_v2.pkl", "wb") as file:
159
+ pickle.dump(modelo2, file)
160
+
161
+ with open("modelos//poly_features_v2.pkl", "wb") as file:
162
+ pickle.dump(poly, file)
@@ -0,0 +1,77 @@
1
+ from sarapy.utils.plotting import plotTemporalData
2
+ import pandas as pd
3
+ import numpy as np
4
+ import os
5
+ import sarapy.utils.getRawOperations as getRawOperations
6
+ from sarapy.dataProcessing import OpsProcessor
7
+ from sarapy.preprocessing import TransformInputData
8
+ from sarapy.dataProcessing import TLMSensorDataProcessor
9
+ import sarapy.stats.stats as stats
10
+
11
+ tlmsde = TLMSensorDataProcessor.TLMSensorDataProcessor()
12
+
13
+ nodo = "UPM017N"
14
+
15
+ data_path = os.path.join(os.getcwd(), f"examples\\2025-04-10\\{nodo}\\data.json")
16
+ historical_data_path = os.path.join(os.getcwd(), f"examples\\2025-04-10\\{nodo}\\historical-data.json")
17
+
18
+ raw_data = pd.read_json(data_path, orient="records").to_dict(orient="records")
19
+ raw_data2 = pd.read_json(historical_data_path, orient="records").to_dict(orient="records")
20
+
21
+ transform_input_data = TransformInputData.TransformInputData()
22
+
23
+ raw_ops = getRawOperations.getRawOperations(raw_data, raw_data2)
24
+ datum = transform_input_data.fit_transform(raw_ops)[:,2]
25
+ telemetria = tlmsde.fit_transform(datum)
26
+ mode = telemetria[:,tlmsde.dataPositions["MODEFlag"]]
27
+ dstpt = telemetria[:,tlmsde.dataPositions["DSTRPT"]]
28
+
29
+ op = OpsProcessor.OpsProcessor(classifier_file='modelos\\pipeline_rf.pkl', imputeDistances = False,
30
+ regresor_file='modelos\\regresor.pkl', poly_features_file='modelos\\poly_features.pkl')
31
+ op.operationsDict
32
+ data_processed = op.processOperations(raw_ops)
33
+
34
+ #paso la lista de operaciones a un dataframe
35
+ df = pd.DataFrame(data_processed)
36
+ df["mode"] = mode
37
+ df["dstpt"] = dstpt
38
+ df["nodo"] = nodo
39
+ ma = stats.getMA(df["dstpt"].values, window_size=104, mode='same')
40
+ df["dstpt_ma"] = ma
41
+ ##me quedo con los datos donde mode==0
42
+ df = df[df["mode"] == 0]
43
+
44
+ #calculo el resumen del sensor
45
+ resumen = stats.resumen_sensor(df, values_col="dstpt_ma", pctbajo_value=1, pctalto_value=14)
46
+ print(resumen)
47
+ #calculo la probabilidad de saturación
48
+ prob_saturacion = stats.calcular_prob_saturacion(ma[2000:], saturation_mode="alto", umbrales=(1, 14),
49
+ alpha=0.2, beta=0.2)
50
+ print(f"Probabilidad de saturación: {prob_saturacion}")
51
+
52
+ # Definimos grilla de alpha y beta
53
+ alpha_vals = np.linspace(0, 1, 20)
54
+ beta_vals = np.linspace(0, 1, 20)
55
+
56
+ # Creamos matriz de resultados
57
+ Psat_matrix = np.zeros((len(alpha_vals), len(beta_vals)))
58
+
59
+ for i, alpha in enumerate(alpha_vals):
60
+ for j, beta in enumerate(beta_vals):
61
+ Psat = prob_saturacion = stats.calcular_prob_saturacion(ma, saturation_mode="alto", umbrales=(1, 14),
62
+ alpha=alpha, beta=beta)
63
+ Psat_matrix[i, j] = Psat
64
+
65
+ import matplotlib.pyplot as plt
66
+ import seaborn as sns
67
+
68
+ plt.figure(figsize=(10, 8))
69
+ sns.heatmap(Psat_matrix, xticklabels=np.round(beta_vals, 2), yticklabels=np.round(alpha_vals, 2), cmap="coolwarm")
70
+ plt.title("Evolución de Psat en función de α (vertical) y β (horizontal)")
71
+ plt.xlabel("β (peso de kurtosis)")
72
+ plt.ylabel("α (peso de skewness)")
73
+ plt.show()
74
+
75
+ colors = ["#0b3256","#fa0000"]
76
+ plotTemporalData(df, nodos = [nodo], columnas = ["dstpt_ma"], title = "DSTPT",sameFig = False, show = True,
77
+ save = False, filename = "dstpt_plot.png", figsize=(15, 10), colors=colors)
@@ -0,0 +1,5 @@
1
+ def test_import():
2
+ import sarapy
3
+
4
+
5
+ test_import()
@@ -1,21 +0,0 @@
1
- [project]
2
- name = "sarapy"
3
-
4
- version = "3.0.0"
5
- authors = [
6
- {name = "Lucas Baldezzari", email = "lmbaldezzari@gmail.com"},]
7
- maintainers = [
8
- {name = "Lucas Baldezzari", email = "lmbaldezzari@gmail.com"}
9
- ]
10
-
11
- dependencies = [
12
- "numpy",
13
- "matplotlib",
14
- "pandas",
15
- "scipy",
16
- "scikit-learn",
17
- "geopy",
18
- ]
19
-
20
- readme = "README.md"
21
- license = {text = "For private use only. Owner AMG Servicios profesionales (Mercedes, Uruguay)"}
@@ -1,70 +0,0 @@
1
- import pickle
2
- import logging
3
- from sarapy.dataProcessing import TLMSensorDataProcessor
4
-
5
- class FertilizerTransformer:
6
- """
7
- Clase para tomar los valores de distorsión de fertilizante y transformarlos a gramos
8
- """
9
-
10
- def __init__(self, regresor_file, poly_features_file):
11
- """Constructor de la clase FertilizerImputer.
12
-
13
- Args:
14
- - regresor: Regresor que transforma los valores de distorsión a gramos.
15
- - poly_features: Grado del polinomio a utilizar en la transformación de los datos.
16
- """
17
- self.logger = logging.getLogger("FertilizerTransformer")
18
- ##cargo el regresor con pickle. Usamos try para capturar el error FileNotFoundError
19
- try:
20
- with open(regresor_file, 'rb') as file:
21
- self._regresor = pickle.load(file)
22
- self.logger.info("Regresor cargado con éxito.")
23
- except FileNotFoundError:
24
- self.logger.error("El archivo no se encuentra en el directorio actual.")
25
-
26
- ##cargo las características polinómicas con pickle. Usamos try para capturar el error FileNotFoundError
27
- try:
28
- with open(poly_features_file, 'rb') as file:
29
- self._poly_features = pickle.load(file)
30
- self.logger.info("Características polinómicas cargadas con éxito.")
31
- except FileNotFoundError:
32
- self.logger.error("El archivo no se encuentra en el directorio actual.")
33
-
34
- self.fertilizer_grams = None ##cuando no se ha transformado ningún dato, se inicializa en None
35
-
36
-
37
- def transform(self, data):
38
- """Transforma los datos de distorsión de fertilizante a gramos.
39
-
40
- Params:
41
- - data: Es una lista de diccionarios (como un JSON) con los datos de telemetría.
42
-
43
- Returns:
44
- - 0: Array con los valores de distorsión de fertilizante transformados a gramos.
45
- """
46
- tlmDataProcessor = TLMSensorDataProcessor.TLMSensorDataProcessor(data)
47
- X = tlmDataProcessor["SC_FT",:]
48
- X_poly = self._poly_features.fit_transform(X.reshape(-1, 1))
49
- self.fertilizer_grams = self._regresor.predict(X_poly)
50
-
51
- ##retorno con shape (n,)
52
- return self.fertilizer_grams.reshape(-1,)
53
-
54
- if __name__ == "__main__":
55
- import pandas as pd
56
- import json
57
- from sarapy.preprocessing import TransformInputData
58
-
59
- historical_data_path = "examples/2025-06-21/UPM000N/historical-data.json"
60
- with open(historical_data_path, 'r') as file:
61
- historical_data = json.load(file)
62
-
63
- ##cargo en un diccionario sarapy\preprocessing\telemetriaDataPosition.json
64
- data_positions = json.load(open("sarapy/preprocessing/telemetriaDataPosition.json", 'r'))
65
- transform_input_data = TransformInputData.TransformInputData()
66
- transformed_data = transform_input_data.transform(historical_data)
67
-
68
- fertransformer = FertilizerTransformer(regresor_file='modelos\\regresor.pkl', poly_features_file='modelos\\poly_features.pkl')
69
- gramos = fertransformer.transform(transformed_data)
70
- print(gramos[:10])
@@ -1,6 +0,0 @@
1
- numpy
2
- matplotlib
3
- pandas
4
- scipy
5
- scikit-learn
6
- geopy
@@ -1 +0,0 @@
1
- sarapy
sarapy-3.0.0/setup.py DELETED
@@ -1,35 +0,0 @@
1
- from setuptools import setup, find_packages
2
- import toml
3
-
4
- def getRequirements():
5
- with open('requirements.txt', 'r') as f:
6
- requirements = f.read().splitlines()
7
- return requirements
8
-
9
- def readme():
10
- with open('README.md') as f:
11
- return f.read()
12
-
13
- def version():
14
- with open('pyproject.toml') as f:
15
- return toml.load(f)['project']['version']
16
-
17
- setup(
18
- name='sarapy',
19
- version=version(),
20
- packages=find_packages(),
21
- install_requires=getRequirements(),
22
- author='Lucas Baldezzari',
23
- author_email='lmbaldezzari@gmail.com',
24
- description='Library for Sarapico Metadata processing',
25
- long_description=readme(),
26
- url='https://github.com/lucasbaldezzari/sarapy',
27
- license='MIT', ##revisar licencia
28
- classifiers=[
29
- 'License :: OSI Approved :: MIT License',
30
- 'Programming Language :: Python :: 3',
31
- 'Operating System :: Microsoft :: Windows :: Windows 10',
32
- 'Operating System :: Microsoft :: Windows :: Windows 11',
33
- 'Operating System :: Unix',
34
- ],
35
- )
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes