Spaces:
Runtime error
Runtime error
File size: 8,176 Bytes
9ac5ea2 ebe86df 38e70c4 ebe86df fe8da28 38e70c4 ebe86df c30da09 b5bfbc4 9ac5ea2 c30da09 fe8da28 b5bfbc4 38e70c4 fe8da28 38e70c4 c30da09 e3dc221 c30da09 38e70c4 ffd3765 9ac5ea2 e3dc221 38e70c4 fe8da28 38e70c4 9ac5ea2 38e70c4 b5bfbc4 38e70c4 9ac5ea2 b5bfbc4 fe8da28 b5bfbc4 fe8da28 b5bfbc4 fe8da28 b5bfbc4 fe8da28 b5bfbc4 9ac5ea2 b5bfbc4 fe8da28 38e70c4 fe8da28 38e70c4 fe8da28 38e70c4 9ac5ea2 fe8da28 38e70c4 fe8da28 38e70c4 bd334dc 38e70c4 bd334dc 12e35a6 38e70c4 |
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 |
import collections
import os
from datetime import datetime, timedelta
import json
from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import parse_qs, urlparse
from huggingface_hub import list_datasets, set_access_token, HfFolder
from datasets import load_dataset, DatasetDict, Dataset
import numpy as np
HF_TOKEN = os.environ['HF_TOKEN']
set_access_token(HF_TOKEN)
HfFolder.save_token(HF_TOKEN)
datasets = {
"stars": load_dataset("open-source-metrics/stars").sort('dates'),
"issues": load_dataset("open-source-metrics/issues").sort('dates'),
"pip": load_dataset("open-source-metrics/pip").sort('day')
}
val = 0
def _range(e):
global val
e['range'] = val
val += 1
return e
stars = {}
for k, v in datasets['stars'].items():
stars[k] = v.map(_range)
val = 0
issues = {}
for k, v in datasets['issues'].items():
issues[k] = v.map(_range)
val = 0
datasets['stars'] = DatasetDict(**stars)
datasets['issues'] = DatasetDict(**issues)
# datasets = {
# k1: DatasetDict({
# k2: v2.select(range(0, len(v2), max(1, int(len(v2) / 1000)))) for k2, v2 in v1.items()
# }) for k1, v1 in datasets.items()
# }
def link_values(library_names, returned_values):
previous_values = {library_name: None for library_name in library_names}
for library_name in library_names:
for i in returned_values.keys():
if library_name not in returned_values[i]:
returned_values[i][library_name] = previous_values[library_name]
else:
previous_values[library_name] = returned_values[i][library_name]
return returned_values
def running_mean(x, N, total_length=-1):
cumsum = np.cumsum(np.insert(x, 0, 0))
to_pad = max(total_length - len(cumsum), 0)
return np.pad(cumsum[N:] - cumsum[:-N], (to_pad, 0)) / float(N)
class RequestHandler(SimpleHTTPRequestHandler):
def do_GET(self):
print(self.path)
if self.path == "/":
self.path = "index.html"
return SimpleHTTPRequestHandler.do_GET(self)
if self.path.startswith("/initialize"):
dataset_keys = {k: set(v.keys()) for k, v in datasets.items()}
dataset_with_most_splits = max([d for d in dataset_keys.values()], key=len)
warnings = []
for k, v in dataset_keys.items():
if len(v) < len(dataset_with_most_splits):
warnings.extend(f"The {k} dataset does not contain all splits. Missing: {dataset_with_most_splits - v}")
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
# TODO: Send and display warnings
dataset_with_most_splits = list(dataset_with_most_splits)
dataset_with_most_splits.sort()
self.wfile.write(json.dumps(list(dataset_with_most_splits)).encode("utf-8"))
return SimpleHTTPRequestHandler
if self.path.startswith("/retrievePipInstalls"):
url = urlparse(self.path)
query = parse_qs(url.query)
library_names = query.get("input", None)[0]
library_names = library_names.split(',')
if 'Cumulated' in library_names:
dataset_keys = {k: set(v.keys()) for k, v in datasets.items()}
dataset_with_most_splits = max([d for d in dataset_keys.values()], key=len)
library_names = list(dataset_with_most_splits)
returned_values = {}
for library_name in library_names:
for i in datasets['pip'][library_name]:
if i['day'] in returned_values:
returned_values[i['day']]['Cumulated'] += i['num_downloads']
else:
returned_values[i['day']] = {'Cumulated': i['num_downloads']}
library_names = ['Cumulated']
else:
returned_values = {}
for library_name in library_names:
for i in datasets['pip'][library_name]:
if i['day'] in returned_values:
returned_values[i['day']][library_name] = i['num_downloads']
else:
returned_values[i['day']] = {library_name: i['num_downloads']}
for library_name in library_names:
for i in returned_values.keys():
if library_name not in returned_values[i]:
returned_values[i][library_name] = None
returned_values = collections.OrderedDict(sorted(returned_values.items()))
output = {l: [k[l] for k in returned_values.values()] for l in library_names}
output['day'] = list(returned_values.keys())
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps(output).encode("utf-8"))
return SimpleHTTPRequestHandler
if self.path.startswith("/retrieveStars"):
url = urlparse(self.path)
query = parse_qs(url.query)
library_names = query.get("input", None)[0]
library_names = library_names.split(',')
returned_values = {}
dataset_dict = datasets['stars']
for library_name in library_names:
dataset = dataset_dict[library_name]
for i in dataset:
if i['dates'] in returned_values:
returned_values[i['dates']][library_name] = i['range']
else:
returned_values[i['dates']] = {library_name: i['range']}
returned_values = collections.OrderedDict(sorted(returned_values.items()))
returned_values = link_values(library_names, returned_values)
output = {l: [k[l] for k in returned_values.values()][::-1] for l in library_names}
output['day'] = list(returned_values.keys())[::-1]
# Trim down to a smaller number of points.
output = {k: [v for i, v in enumerate(value) if i % int(len(value) / 100) == 0] for k, value in output.items()}
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps(output).encode("utf-8"))
return SimpleHTTPRequestHandler
if self.path.startswith("/retrieveIssues"):
url = urlparse(self.path)
query = parse_qs(url.query)
library_names = query.get("input", None)[0]
library_names = library_names.split(',')
returned_values = {}
dataset_dict = datasets['issues']
for library_name in library_names:
dataset = dataset_dict[library_name]
for i in dataset:
if i['dates'] in returned_values:
returned_values[i['dates']][library_name] = i['range']
else:
returned_values[i['dates']] = {library_name: i['range']}
returned_values = collections.OrderedDict(sorted(returned_values.items()))
returned_values = link_values(library_names, returned_values)
output = {l: [k[l] for k in returned_values.values()][::-1] for l in library_names}
output['day'] = list(returned_values.keys())[::-1]
# Trim down to a smaller number of points.
output = {k: [v for i, v in enumerate(value) if i % int(len(value) / 100) == 0] for k, value in output.items()}
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps(output).encode("utf-8"))
return SimpleHTTPRequestHandler
return SimpleHTTPRequestHandler.do_GET(self)
server = ThreadingHTTPServer(("", 7860), RequestHandler)
print("Running on port 7860")
server.serve_forever()
|