Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
File size: 20,833 Bytes
de86128 46c15e8 de86128 1581d20 de86128 1581d20 de86128 1581d20 613ab12 1581d20 613ab12 1581d20 613ab12 1581d20 613ab12 1581d20 de86128 1581d20 de86128 1581d20 46c15e8 1581d20 46c15e8 1581d20 46c15e8 1581d20 46c15e8 1581d20 de86128 1581d20 de86128 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 |
import streamlit as st
import pandas as pd
from datasets import load_dataset
from ast import literal_eval
import altair as alt
import plotly.graph_objs as go
import matplotlib.pyplot as plt
def main():
print("Build")
nlp_tasks = ["text-classification", "text-generation", "text2text-generation", "token-classification", "fill-mask", "question-answering",
"translation", "conversational", "sentence-similarity", "summarization", "multiple-choice", "zero-shot-classification", "table-question-answering"
]
audio_tasks = ["automatic-speech-recognition", "audio-classification", "text-to-speech", "audio-to-audio", "voice-activity-detection"]
cv_tasks = ["image-classification", "image-segmentation", "zero-shot-image-classification", "image-to-image", "unconditional-image-generation", "object-detection"]
multimodal = ["feature-extraction", "text-to-image", "visual-question-answering", "image-to-text", "document-question-answering"]
tabular = ["tabular-classification", "tabular-regression"]
modalities = {
"nlp": nlp_tasks,
"audio": audio_tasks,
"cv": cv_tasks,
"multimodal": multimodal,
"tabular": tabular,
"rl": ["reinforcement-learning"]
}
def modality(row):
pipeline = row["pipeline"]
for modality, tasks in modalities.items():
if pipeline in tasks:
return modality
if type(pipeline) == "str":
return "unk_modality"
return None
supported_revisions = ["27_09_22"]
st.cache(allow_output_mutation=True)
def process_dataset(version):
# Load dataset at specified revision
dataset = load_dataset("open-source-metrics/model-repos-stats", revision=version)
# Convert to pandas dataframe
data = dataset["train"].to_pandas()
# Add modality column
data["modality"] = data.apply(modality, axis=1)
# Bin the model card length into some bins
data["length_bins"] = pd.cut(data["text_length"], [0, 200, 1000, 2000, 3000, 4000, 5000, 7500, 10000, 20000, 50000])
return data
base = st.selectbox(
'What revision do you want to use',
supported_revisions)
data = process_dataset(base)
def eval_tags(row):
tags = row["tags"]
if tags == "none" or tags == [] or tags == "{}":
return []
if tags[0] != "[":
tags = str([tags])
val = literal_eval(tags)
if isinstance(val, dict):
return []
return val
data["tags"] = data.apply(eval_tags, axis=1)
total_samples = data.shape[0]
st.metric(label="Total models", value=total_samples)
# Tabs don't work in Spaces st version
#tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8 = st.tabs(["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super users", "Raw Data"])
tab = st.selectbox(
'Topic of interest',
["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super Users", "Raw Data"])
# with tab1:
if tab == "Language":
st.header("Languages info")
data.loc[data.languages == "False", 'languages'] = None
data.loc[data.languages == {}, 'languages'] = None
no_lang_count = data["languages"].isna().sum()
data["languages"] = data["languages"].fillna('none')
def make_list(row):
languages = row["languages"]
if languages == "none":
return []
return literal_eval(languages)
def language_count(row):
languages = row["languages"]
leng = len(languages)
return leng
data["languages"] = data.apply(make_list, axis=1)
data["language_count"] = data.apply(language_count, axis=1)
models_with_langs = data[data["language_count"] > 0]
langs = models_with_langs["languages"].explode()
langs = langs[langs != {}]
total_langs = len(langs.unique())
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="Language Specified", value=total_samples-no_lang_count)
with col2:
st.metric(label="No Language Specified", value=no_lang_count)
with col3:
st.metric(label="Total Unique Languages", value=total_langs)
st.subheader("Count of languages per model repo")
st.text("Some repos are for multiple languages, so the count is greater than 1")
linguality = st.selectbox(
'All or just Multilingual',
["All", "Just Multilingual", "Three or more languages"])
filter = 0
st.text("Tofix: This just takes into account count of languages, it misses the multilingual tag")
if linguality == "Just Multilingual":
filter = 1
elif linguality == "Three or more languages":
filter = 2
models_with_langs = data[data["language_count"] > filter]
df1 = models_with_langs['language_count'].value_counts()
st.bar_chart(df1)
st.subheader("Most frequent languages")
linguality_2 = st.selectbox(
'All or filtered',
["All", "No English", "Remove top 10"])
filter = 0
if linguality_2 == "All":
filter = 0
elif linguality_2 == "No English":
filter = 1
else:
filter = 2
models_with_langs = data[data["language_count"] > 0]
langs = models_with_langs["languages"].explode()
langs = langs[langs != {}]
orig_d = langs.value_counts().rename_axis("language").to_frame('counts').reset_index()
d = orig_d
if filter == 1:
d = orig_d.iloc[1:]
elif filter == 2:
d = orig_d.iloc[10:]
# Just keep top 25 to avoid vertical scroll
d = d.iloc[:25]
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('language', sort=None)
))
st.subheader("Raw Data")
l = df1.rename_axis("lang_count").reset_index().rename(columns={"language_count": "repos_count"})
st.dataframe(l)
d = orig_d.astype(str)
st.dataframe(d)
#with tab2:
if tab == "License":
st.header("License info")
no_license_count = data["license"].isna().sum()
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="License Specified", value=total_samples-no_license_count)
with col2:
st.metric(label="No license Specified", value=no_license_count)
with col3:
st.metric(label="Total Unique Licenses", value=len(data["license"].unique()))
st.subheader("Distribution of licenses per model repo")
license_filter = st.selectbox(
'All or filtered',
["All", "No Apache 2.0", "Remove top 10"])
filter = 0
if license_filter == "All":
filter = 0
elif license_filter == "No Apache 2.0":
filter = 1
else:
filter = 2
d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
if filter == 1:
d = d.iloc[1:]
elif filter == 2:
d = d.iloc[10:]
# Just keep top 25 to avoid vertical scroll
d = d.iloc[:25]
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('license', sort=None)
))
st.text("There are some edge cases, as old repos using lists of licenses.")
st.subheader("Raw Data")
d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
st.dataframe(d)
#with tab3:
if tab == "Pipeline":
st.header("Pipeline info")
tags = data["tags"].explode()
tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
s = tags["tag"]
s = s[s.apply(type) == str]
unique_tags = len(s.unique())
no_pipeline_count = data["pipeline"].isna().sum()
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="# models that have any pipeline", value=total_samples-no_pipeline_count)
with col2:
st.metric(label="No pipeline Specified", value=no_pipeline_count)
with col3:
st.metric(label="Total Unique Pipelines", value=len(data["pipeline"].unique()))
pipeline_filter = st.selectbox(
'Modalities',
["All", "NLP", "CV", "Audio", "RL", "Multimodal", "Tabular"])
filter = 0
if pipeline_filter == "All":
filter = 0
elif pipeline_filter == "NLP":
filter = 1
elif pipeline_filter == "CV":
filter = 2
elif pipeline_filter == "Audio":
filter = 3
elif pipeline_filter == "RL":
filter = 4
elif pipeline_filter == "Multimodal":
filter = 5
elif pipeline_filter == "Tabular":
filter = 6
st.subheader("High-level metrics")
filtered_data = data[data['pipeline'].notna()]
if filter == 1:
filtered_data = data[data["modality"] == "nlp"]
elif filter == 2:
filtered_data = data[data["modality"] == "cv"]
elif filter == 3:
filtered_data = data[data["modality"] == "audio"]
elif filter == 4:
filtered_data = data[data["modality"] == "rl"]
elif filter == 5:
filtered_data = data[data["modality"] == "multimodal"]
elif filter == 6:
filtered_data = data[data["modality"] == "tabular"]
col1, col2, col3 = st.columns(3)
with col1:
p = st.selectbox(
'What pipeline do you want to see?',
["all", *filtered_data["pipeline"].unique()]
)
with col2:
l = st.selectbox(
'What library do you want to see?',
["all", *filtered_data["library"].unique()]
)
with col3:
f = st.selectbox(
'What framework support? (transformers)',
["all", "py", "tf", "jax"]
)
col1, col2 = st.columns(2)
with col1:
filt = st.multiselect(
label="Tags (All by default)",
options=s.unique(),
default=None)
with col2:
o = st.selectbox(
label="Operation (for tags)",
options=["Any", "All", "None"]
)
def filter_fn(row):
tags = row["tags"]
tags[:] = [d for d in tags if isinstance(d, str)]
if o == "All":
if all(elem in tags for elem in filt):
return True
s1 = set(tags)
s2 = set(filt)
if o == "Any":
if bool(s1 & s2):
return True
if o == "None":
if len(s1.intersection(s2)) == 0:
return True
return False
if p != "all":
filtered_data = filtered_data[filtered_data["pipeline"] == p]
if l != "all":
filtered_data = filtered_data[filtered_data["library"] == l]
if f != "all":
if f == "py":
filtered_data = filtered_data[filtered_data["pytorch"] == 1]
elif f == "tf":
filtered_data = filtered_data[filtered_data["tensorflow"] == 1]
elif f == "jax":
filtered_data = filtered_data[filtered_data["jax"] == 1]
if filt != []:
filtered_data = filtered_data[filtered_data.apply(filter_fn, axis=1)]
d = filtered_data["pipeline"].value_counts().rename_axis("pipeline").to_frame('counts').reset_index()
columns_of_interest = ["downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
grouped_data = filtered_data.groupby("pipeline").sum()[columns_of_interest]
final_data = pd.merge(
d, grouped_data, how="outer", on="pipeline"
)
sums = grouped_data.sum()
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="Total models", value=filtered_data.shape[0])
with col2:
st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
with col3:
st.metric(label="Cumulative likes", value=sums["likes"])
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="Total in PT", value=sums["pytorch"])
with col2:
st.metric(label="Total in TF", value=sums["tensorflow"])
with col3:
st.metric(label="Total in JAX", value=sums["jax"])
st.metric(label="Unique Tags", value=unique_tags)
st.subheader("Count of models per pipeline")
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('pipeline', sort=None)
))
st.subheader("Aggregated data")
st.dataframe(final_data)
st.subheader("Most common model types (specific to transformers)")
d = filtered_data["model_type"].value_counts().rename_axis("model_type").to_frame('counts').reset_index()
d = d.iloc[:15]
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('model_type', sort=None)
))
st.subheader("Most common library types (Learn more in library tab)")
d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('library', sort=None)
))
st.subheader("Tags by count")
tags = filtered_data["tags"].explode()
tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
st.write(alt.Chart(tags.head(30)).mark_bar().encode(
x='counts',
y=alt.X('tag', sort=None)
))
st.subheader("Raw Data")
columns_of_interest = [
"repo_id", "author", "model_type", "files_per_repo", "library",
"downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
raw_data = filtered_data[columns_of_interest]
st.dataframe(raw_data)
# todo : add activity metric
#with tab4:
if tab == "Discussion Features":
st.header("Discussions Tab info")
columns_of_interest = ["prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]
sums = data[columns_of_interest].sum()
col1, col2, col3, col4 = st.columns(4)
with col1:
st.metric(label="Total PRs", value=sums["prs_count"])
with col2:
st.metric(label="PRs opened", value=sums["prs_open"])
with col3:
st.metric(label="PRs merged", value=sums["prs_merged"])
with col4:
st.metric(label="PRs closed", value=sums["prs_closed"])
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="Total discussions", value=sums["discussions_count"])
with col2:
st.metric(label="Discussions open", value=sums["discussions_open"])
with col3:
st.metric(label="Discussions closed", value=sums["discussions_closed"])
filtered_data = data[["repo_id", "prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]].sort_values("prs_count", ascending=False).reset_index(drop=True)
st.dataframe(filtered_data)
#with tab5:
if tab == "Libraries":
st.header("Library info")
no_library_count = data["library"].isna().sum()
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="# models that have any library", value=total_samples-no_library_count)
with col2:
st.metric(label="No library Specified", value=no_library_count)
with col3:
st.metric(label="Total Unique library", value=len(data["library"].unique()))
st.subheader("High-level metrics")
filtered_data = data[data['library'].notna()]
col1, col2 = st.columns(2)
with col1:
lib = st.selectbox(
'What library do you want to see? ',
["all", *filtered_data["library"].unique()]
)
with col2:
pip = st.selectbox(
'What pipeline do you want to see? ',
["all", *filtered_data["pipeline"].unique()]
)
if pip != "all":
filtered_data = filtered_data[filtered_data["pipeline"] == pip]
if lib != "all":
filtered_data = filtered_data[filtered_data["library"] == lib]
d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index()
grouped_data = filtered_data.groupby("library").sum()[["downloads_30d", "likes"]]
final_data = pd.merge(
d, grouped_data, how="outer", on="library"
)
sums = grouped_data.sum()
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="Total models", value=filtered_data.shape[0])
with col2:
st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
with col3:
st.metric(label="Cumulative likes", value=sums["likes"])
st.subheader("Most common library types (Learn more in library tab)")
d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
st.write(alt.Chart(d).mark_bar().encode(
x='counts',
y=alt.X('library', sort=None)
))
st.subheader("Aggregated Data")
st.dataframe(final_data)
st.subheader("Raw Data")
columns_of_interest = ["repo_id", "author", "files_per_repo", "library", "downloads_30d", "likes"]
filtered_data = filtered_data[columns_of_interest]
st.dataframe(filtered_data)
#with tab6:
if tab == "Model Cards":
st.header("Model cards")
columns_of_interest = ["has_model_index", "has_metadata", "has_text", "text_length"]
rows = data.shape[0]
cond = data["has_model_index"] | data["has_text"]
with_model_card = data[cond]
c_model_card = with_model_card.shape[0]
st.subheader("High-level metrics")
col1, col2, col3 = st.columns(3)
with col1:
st.metric(label="# models with model card file", value=c_model_card)
with col2:
st.metric(label="# models without model card file", value=rows-c_model_card)
with_index = data["has_model_index"].sum()
with col1:
st.metric(label="# models with model index", value=with_index)
with col2:
st.metric(label="# models without model index", value=rows-with_index)
with_text = data["has_text"]
with col1:
st.metric(label="# models with model card text", value=with_text.sum())
with col2:
st.metric(label="# models without model card text", value=rows-with_text.sum())
st.subheader("Length (chars) of model card content")
fig, ax = plt.subplots()
ax = data["length_bins"].value_counts().plot.bar()
st.metric(label="# average length of model card (chars)", value=data[with_text]["text_length"].mean())
st.pyplot(fig)
st.subheader("Tags (Read more in Pipeline tab)")
tags = data["tags"].explode()
tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
st.write(alt.Chart(tags.head(30)).mark_bar().encode(
x='counts',
y=alt.X('tag', sort=None)
))
#with tab7:
if tab == "Super Users":
st.header("Authors")
st.text("This info corresponds to the repos owned by the authors")
authors = data.groupby("author").sum().drop(["text_length", "Unnamed: 0"], axis=1).sort_values("downloads_30d", ascending=False)
d = data["author"].value_counts().rename_axis("author").to_frame('counts').reset_index()
final_data = pd.merge(
d, authors, how="outer", on="author"
)
st.dataframe(final_data)
#with tab2:
if tab == "Raw Data":
st.header("Raw Data")
d = data.astype(str)
st.dataframe(d)
if __name__ == '__main__':
main()
|