File size: 11,279 Bytes
c9117ba 66ac827 f1c0686 7bd4b6e f1c0686 7bd4b6e f1c0686 7bd4b6e f1c0686 7bd4b6e f1c0686 66ac827 f1c0686 7bd4b6e f1c0686 66ac827 f1c0686 7bd4b6e 66ac827 3c24662 66ac827 3c24662 66ac827 3c24662 66ac827 3c24662 66ac827 3c24662 66ac827 f1c0686 3efb4a6 66ac827 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 |
from huggingface_hub import login
from datasets import load_dataset, Dataset, concatenate_datasets
import json
from src.services.util import HF_TOKEN, DATASET_NAME
def init_huggingface():
"""Initialize Hugging Face authentication."""
if HF_TOKEN is None:
raise ValueError(
"Hugging Face token not found in environment variables.")
login(token=HF_TOKEN)
def update_dataset(json_data):
"""Update the Hugging Face dataset with new data."""
if json_data is None or json_data.startswith("The following fields are required"):
return json_data or "No data to submit. Please fill in all required fields."
try:
data = json.loads(json_data)
except json.JSONDecodeError:
return "Invalid JSON data. Please ensure all required fields are filled correctly."
try:
dataset = load_dataset(DATASET_NAME, split="train")
print(dataset)
except:
dataset = Dataset.from_dict({})
new_data = create_flattened_data(data)
new_dataset = Dataset.from_dict(new_data)
if len(dataset) > 0:
print("dataset intitial")
print(dataset)
print("data to add ")
print(new_dataset)
updated_dataset = concatenate_datasets([dataset, new_dataset])
else:
updated_dataset = new_dataset
updated_dataset.push_to_hub(DATASET_NAME)
return "Data submitted successfully and dataset updated!"
def create_flattened_data(data):
"""Create a flattened data structure for the algorithms."""
# Handle algorithms
algorithms = data.get("task", {}).get("algorithms", [])
fields = ["trainingType", "algorithmType", "algorithmName", "algorithmUri", "foundationModelName", "foundationModelUri",
"parametersNumber", "framework", "frameworkVersion", "classPath", "layersNumber", "epochsNumber", "optimizer", "quantization"]
"""Create a flattened data structure for the algorithms."""
algorithms_data = {field: "| ".join(str(algo.get(
field)) for algo in algorithms if algo.get(field)) or "" for field in fields}
trainingType_str = algorithms_data["trainingType"]
algorithmType_str = algorithms_data["algorithmType"]
algorithmName_str = algorithms_data["algorithmName"]
algorithmUri_str = algorithms_data["algorithmUri"]
foundationModelName_str = algorithms_data["foundationModelName"]
foundationModelUri_str = algorithms_data["foundationModelUri"]
parametersNumber_str = algorithms_data["parametersNumber"]
framework_str = algorithms_data["framework"]
frameworkVersion_str = algorithms_data["frameworkVersion"]
classPath_str = algorithms_data["classPath"]
layersNumber_str = algorithms_data["layersNumber"]
epochsNumber_str = algorithms_data["epochsNumber"]
optimizer_str = algorithms_data["optimizer"]
quantization_str = algorithms_data["quantization"]
"""Create a flattened data structure for the dataset."""
# Handle dataset
dataset = data.get("task", {}).get("dataset", [])
fields = ["dataUsage", "dataType", "dataFormat", "dataSize",
"dataQuantity", "shape", "source", "sourceUri", "owner"]
"""Create a flattened data structure for the dataset."""
dataset_data = {field: "| ".join(
str(d.get(field)) for d in dataset if d.get(field)) or "" for field in fields}
dataUsage_str = dataset_data["dataUsage"]
dataType_str = dataset_data["dataType"]
dataFormat_str = dataset_data["dataFormat"]
dataSize_str = dataset_data["dataSize"]
dataQuantity_str = dataset_data["dataQuantity"]
shape_str = dataset_data["shape"]
source_str = dataset_data["source"]
sourceUri_str = dataset_data["sourceUri"]
owner_str = dataset_data["owner"]
"""Create a flattened data structure for the measures."""
# Handle measures
measures = data.get("measures", [])
fields = ["measurementMethod", "manufacturer", "version", "cpuTrackingMode", "gpuTrackingMode", "averageUtilizationCpu", "averageUtilizationGpu",
"powerCalibrationMeasurement", "durationCalibrationMeasurement", "powerConsumption", "measurementDuration", "measurementDateTime"]
"""Create a flattened data structure for the measures."""
measures_data = {field: "| ".join(str(measure.get(
field)) for measure in measures if measure.get(field)) or "" for field in fields}
measurementMethod_str = measures_data["measurementMethod"]
manufacturer_str = measures_data["manufacturer"]
version_str = measures_data["version"]
cpuTrackingMode_str = measures_data["cpuTrackingMode"]
gpuTrackingMode_str = measures_data["gpuTrackingMode"]
averageUtilizationCpu_str = measures_data["averageUtilizationCpu"]
averageUtilizationGpu_str = measures_data["averageUtilizationGpu"]
powerCalibrationMeasurement_str = measures_data["powerCalibrationMeasurement"]
durationCalibrationMeasurement_str = measures_data["durationCalibrationMeasurement"]
powerConsumption_str = measures_data["powerConsumption"]
measurementDuration_str = measures_data["measurementDuration"]
measurementDateTime_str = measures_data["measurementDateTime"]
# Handle components
components = data.get("infrastructure", {}).get("components", [])
fields = ["componentName", "componentType", "nbComponent", "memorySize",
"manufacturer", "family", "series", "share"]
# Generate concatenated strings for each field
component_data = {field: "| ".join(str(comp.get(
field)) for comp in components if comp.get(field)) or "" for field in fields}
componentName_str = component_data["componentName"]
componentType_str = component_data["componentType"]
nbComponent_str = component_data["nbComponent"]
memorySize_str = component_data["memorySize"]
manufacturer_infra_str = component_data["manufacturer"]
family_str = component_data["family"]
series_str = component_data["series"]
share_str = component_data["share"]
return {
# Header
"licensing": [data.get("header", {}).get("licensing", "")],
"formatVersion": [data.get("header", {}).get("formatVersion", "")],
"formatVersionSpecificationUri": [data.get("header", {}).get("formatVersionSpecificationUri", "")],
"reportId": [data.get("header", {}).get("reportId", "")],
"reportDatetime": [data.get("header", {}).get("reportDatetime", "")],
"reportStatus": [data.get("header", {}).get("reportStatus", "")],
"publisher_name": [data.get("header", {}).get("publisher", {}).get("name", "")],
"publisher_division": [data.get("header", {}).get("publisher", {}).get("division", "")],
"publisher_projectName": [data.get("header", {}).get("publisher", {}).get("projectName", "")],
"publisher_confidentialityLevel": [data.get("header", {}).get("publisher", {}).get("confidentialityLevel", "")],
"publisher_publicKey": [data.get("header", {}).get("publisher", {}).get("publicKey", "")],
# Task
"taskStage": [data.get("task", {}).get("taskStage", "")],
"taskFamily": [data.get("task", {}).get("taskFamily", "")],
"nbRequest": [data.get("task", {}).get("nbRequest", "")],
# Algorithms
"trainingType": [trainingType_str],
"algorithmType": [algorithmType_str],
"algorithmName": [algorithmName_str],
"algorithmUri": [algorithmUri_str],
"foundationModelName": [foundationModelName_str],
"foundationModelUri": [foundationModelUri_str],
"parametersNumber": [parametersNumber_str],
"framework": [framework_str],
"frameworkVersion": [frameworkVersion_str],
"classPath": [classPath_str],
"layersNumber": [layersNumber_str],
"epochsNumber": [epochsNumber_str],
"optimizer": [optimizer_str],
"quantization": [quantization_str],
# Dataset
"dataUsage": [dataUsage_str],
"dataType": [dataType_str],
"dataFormat": [dataFormat_str],
"dataSize": [dataSize_str],
"dataQuantity": [dataQuantity_str],
"shape": [shape_str],
"source": [source_str],
"sourceUri": [sourceUri_str],
"owner": [owner_str],
"measuredAccuracy": [data.get("task", {}).get("measuredAccuracy", "")],
"estimatedAccuracy": [data.get("task", {}).get("estimatedAccuracy", "")],
"taskDescription": [data.get("task", {}).get("taskDescription", "")],
# Measures
"measurementMethod": [measurementMethod_str],
"manufacturer": [manufacturer_str],
"version": [version_str],
"cpuTrackingMode": [cpuTrackingMode_str],
"gpuTrackingMode": [gpuTrackingMode_str],
"averageUtilizationCpu": [averageUtilizationCpu_str],
"averageUtilizationGpu": [averageUtilizationGpu_str],
"powerCalibrationMeasurement": [powerCalibrationMeasurement_str],
"durationCalibrationMeasurement": [durationCalibrationMeasurement_str],
"powerConsumption": [powerConsumption_str],
"measurementDuration": [measurementDuration_str],
"measurementDateTime": [measurementDateTime_str],
# System
"os": [data.get("system", {}).get("os", "")],
"distribution": [data.get("system", {}).get("distribution", "")],
"distributionVersion": [data.get("system", {}).get("distributionVersion", "")],
# Software
"language": [data.get("software", {}).get("language", "")],
"version_software": [data.get("software", {}).get("version_software", "")],
# Infrastructure
"infraType": [data.get("infrastructure", {}).get("infra_type", "")],
"cloudProvider": [data.get("infrastructure", {}).get("cloudProvider", "")],
"cloudInstance": [data.get("infrastructure", {}).get("cloudInstance", "")],
"cloudService": [data.get("infrastructure", {}).get("cloudService", "")],
"componentName": [componentName_str],
"componentType": [componentType_str],
"nbComponent": [nbComponent_str],
"memorySize": [memorySize_str],
"manufacturer_infra": [manufacturer_infra_str],
"family": [family_str],
"series": [series_str],
"share": [share_str],
# Environment
"country": [data.get("environment", {}).get("country", "")],
"latitude": [data.get("environment", {}).get("latitude", "")],
"longitude": [data.get("environment", {}).get("longitude", "")],
"location": [data.get("environment", {}).get("location", "")],
"powerSupplierType": [data.get("environment", {}).get("powerSupplierType", "")],
"powerSource": [data.get("environment", {}).get("powerSource", "")],
"powerSourceCarbonIntensity": [data.get("environment", {}).get("powerSourceCarbonIntensity", "")],
# Quality
"quality": [data.get("quality", "")],
}
"""
def create_flattened_data(data):
out = {}
def flatten(x, name=''):
if type(x) is dict:
for a in x:
flatten(x[a], name + a + '_')
elif type(x) is list:
i = 0
for a in x:
flatten(a, name + str(i) + '_')
i += 1
else:
out[name[:-1]] = x
flatten(data)
return out
"""
|