File size: 7,281 Bytes
9079f0c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | import json
import numpy as np
import torch
from transformers import PreTrainedTokenizer
from transformers.tokenization_utils_base import BatchEncoding
class YieldTokenizer(PreTrainedTokenizer):
"""
Adapter tokenizer for FlexServe's built-in text-classification pipeline.
This does NOT tokenize natural language.
It accepts:
- a JSON string, or
- the yield input dictionary
and converts it into:
weather: [B, 52, 6]
soil: [B, 66]
crop_id: [B]
horizon_idx: [B]
Normalization is intentionally NOT performed here.
The sequence-classification model wrapper performs normalization
using statistics stored in config.json.
"""
vocab_files_names = {}
model_input_names = [
"weather",
"soil",
"crop_id",
"horizon_idx",
]
def __init__(
self,
weather_vars=None,
soil_vars=None,
K=52,
eval_cutoffs=None,
**kwargs,
):
self.weather_vars = list(weather_vars or [])
self.soil_vars = list(soil_vars or [])
self.K = int(K)
self.eval_cutoffs = list(
eval_cutoffs
or [20, 24, 28, 32, 36, 40, 44, 48, 52]
)
super().__init__(
pad_token="[PAD]",
unk_token="[UNK]",
**kwargs,
)
@property
def vocab_size(self):
return 2
def get_vocab(self):
return {
"[PAD]": 0,
"[UNK]": 1,
}
def _tokenize(self, text, **kwargs):
return ["[UNK]"]
def _convert_token_to_id(self, token):
return 0 if token == "[PAD]" else 1
def _convert_id_to_token(self, index):
return "[PAD]" if index == 0 else "[UNK]"
def save_vocabulary(self, save_directory, filename_prefix=None):
return ()
def _parse_sample(self, sample):
if isinstance(sample, str):
sample = sample.strip()
try:
sample = json.loads(sample)
except json.JSONDecodeError as exc:
raise ValueError(
"Input must be a valid JSON string."
) from exc
# Handle a JSON string containing another JSON string.
if isinstance(sample, str):
try:
sample = json.loads(sample)
except json.JSONDecodeError as exc:
raise ValueError(
"Input string does not contain valid yield JSON."
) from exc
if not isinstance(sample, dict):
raise ValueError(
"Yield input must be a JSON object/dictionary."
)
crop = str(
sample.get("crop", "corn")
).strip().lower()
if crop not in ("corn", "maize"):
raise ValueError(
"This released model supports corn only."
)
if "weather" not in sample:
raise ValueError(
"Missing 'weather' object."
)
if "soil" not in sample:
raise ValueError(
"Missing 'soil' object."
)
weather_dict = sample["weather"]
soil_dict = sample["soil"]
# --------------------------------------------
# Weather: [52, 6]
# --------------------------------------------
weather_cols = []
for var in self.weather_vars:
if var not in weather_dict:
raise ValueError(
f"Missing weather variable '{var}'."
)
values = np.asarray(
weather_dict[var],
dtype=np.float32,
)
if values.ndim != 1:
raise ValueError(
f"Weather '{var}' must be one-dimensional."
)
if len(values) != self.K:
raise ValueError(
f"Weather '{var}' requires exactly "
f"{self.K} weekly values; received {len(values)}."
)
weather_cols.append(values)
weather = np.stack(
weather_cols,
axis=1,
).astype(np.float32)
# --------------------------------------------
# Soil: [66]
# --------------------------------------------
soil = []
for var in self.soil_vars:
if var not in soil_dict:
raise ValueError(
f"Missing soil variable '{var}'."
)
soil.append(
float(soil_dict[var])
)
soil = np.asarray(
soil,
dtype=np.float32,
)
# --------------------------------------------
# Cutoff
# --------------------------------------------
cutoff = int(
sample.get(
"cutoff",
max(self.eval_cutoffs),
)
)
if cutoff not in self.eval_cutoffs:
raise ValueError(
f"Unsupported cutoff {cutoff}. "
f"Supported cutoffs are {self.eval_cutoffs}."
)
return {
"weather": weather,
"soil": soil,
"crop_id": 0,
"horizon_idx": cutoff,
}
def __call__(
self,
text=None,
text_pair=None,
return_tensors=None,
**kwargs,
):
# --------------------------------------------------
# FlexServe/HF may call tokenizer(**input_dict)
# instead of tokenizer(json_string).
# --------------------------------------------------
if text is None and "weather" in kwargs and "soil" in kwargs:
sample = {
"crop": kwargs.pop("crop", "corn"),
"weather": kwargs.pop("weather"),
"soil": kwargs.pop("soil"),
"cutoff": kwargs.pop(
"cutoff",
max(self.eval_cutoffs),
),
}
samples = [sample]
elif isinstance(text, (list, tuple)):
samples = list(text)
else:
samples = [text]
parsed = [
self._parse_sample(sample)
for sample in samples
]
weather = torch.tensor(
np.stack(
[x["weather"] for x in parsed],
axis=0,
),
dtype=torch.float32,
)
soil = torch.tensor(
np.stack(
[x["soil"] for x in parsed],
axis=0,
),
dtype=torch.float32,
)
crop_id = torch.tensor(
[
x["crop_id"]
for x in parsed
],
dtype=torch.long,
)
horizon_idx = torch.tensor(
[
x["horizon_idx"]
for x in parsed
],
dtype=torch.long,
)
return BatchEncoding(
{
"weather": weather,
"soil": soil,
"crop_id": crop_id,
"horizon_idx": horizon_idx,
}
) |