-
Notifications
You must be signed in to change notification settings - Fork 0
/
fdaapi.py
421 lines (336 loc) · 16.5 KB
/
fdaapi.py
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
import streamlit as st
import requests
import pandas as pd
import time
from datetime import datetime, timedelta
from st_aggrid import AgGrid, GridOptionsBuilder
# Global variables for rate limiting
REQUESTS_PER_MINUTE = 240
REQUESTS_PER_DAY = 120000
last_request_time = time.time()
daily_request_count = 0
last_reset_date = datetime.now().date()
def check_rate_limit():
global last_request_time, daily_request_count, last_reset_date
current_time = time.time()
current_date = datetime.now().date()
# Reset daily count if it's a new day
if current_date > last_reset_date:
daily_request_count = 0
last_reset_date = current_date
# Check if we've exceeded daily limit
if daily_request_count >= REQUESTS_PER_DAY:
st.error("Daily API request limit reached. Please try again tomorrow.")
return False
# Ensure we don't exceed requests per minute
if current_time - last_request_time < 60 / REQUESTS_PER_MINUTE:
time.sleep(60 / REQUESTS_PER_MINUTE - (current_time - last_request_time))
last_request_time = time.time()
daily_request_count += 1
return True
@st.cache_data(ttl=3600)
def get_api_data(field, limit=10):
if not check_rate_limit():
return []
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"count": field,
"limit": limit
}
response = requests.get(url, params=params)
if response.status_code != 200:
st.error(f"API request failed with status code {response.status_code}")
return []
data = response.json()
if 'results' not in data:
st.warning(f"No results found for {field}")
return []
return [item['term'] for item in data['results']][:10] # Limit to first 10 results
@st.cache_data(ttl=3600)
def get_modalities_with_events(limit=100):
if not check_rate_limit():
return []
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"count": "device.generic_name.exact",
"limit": limit
}
response = requests.get(url, params=params)
if response.status_code != 200:
st.error(f"API request failed with status code {response.status_code}")
return []
data = response.json()
if 'results' not in data:
st.warning("No modalities found with adverse events")
return []
return [item['term'] for item in data['results']]
@st.cache_data(ttl=3600)
def get_high_severity_events(limit=100):
if not check_rate_limit():
return []
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"search": "event_type:death",
"limit": limit
}
response = requests.get(url, params=params)
if response.status_code != 200:
st.error(f"API request failed with status code {response.status_code}")
return []
data = response.json()
if 'results' not in data:
st.warning("No high severity events found")
return []
return data['results']
def get_device_events(modality, limit=10):
if not check_rate_limit():
return {}
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"search": f"device.generic_name:'{modality}'",
"limit": min(limit, 1000) # Ensure limit doesn't exceed 1000
}
try:
response = requests.get(url, params=params)
response.raise_for_status()
except requests.exceptions.RequestException as e:
st.error(f"API request failed: {str(e)}")
if response.status_code == 500:
st.error("The FDA server encountered an internal error. This might be due to temporary issues or maintenance. Please try again later or with a smaller number of events.")
return {}
return response.json()
@st.cache_data(ttl=3600)
def get_manufacturer_events(limit=100):
if not check_rate_limit():
return []
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"count": "device.manufacturer_d_name.exact",
"limit": limit
}
response = requests.get(url, params=params)
if response.status_code != 200:
st.error(f"API request failed with status code {response.status_code}")
return []
data = response.json()
if 'results' not in data:
st.warning("No manufacturers found with adverse events")
return []
return data['results']
def get_manufacturer_details(manufacturer, limit=100):
if not check_rate_limit():
return {}
url = "https://api.fda.gov/device/event.json"
params = {
"api_key": "FmMZcDlQm1SHtM2uXegetgdRueXrulaWS1liIegh",
"search": f"device.manufacturer_d_name:'{manufacturer}'",
"limit": limit
}
try:
response = requests.get(url, params=params)
response.raise_for_status() # This will raise an exception for HTTP errors
except requests.exceptions.RequestException as e:
st.error(f"API request failed: {str(e)}")
if response.status_code == 500:
st.error("The FDA server encountered an internal error. This might be due to temporary issues or maintenance. Please try again later.")
elif response.status_code == 400:
st.error("The request was invalid. This might be due to an issue with the manufacturer name format.")
return {}
try:
return response.json()
except ValueError:
st.error("Failed to parse the API response as JSON.")
return {}
def safe_string(value):
if pd.isna(value):
return ''
return str(value)
st.title("FDA Device Adverse Events")
# Create tabs for different features
tab1, tab2, tab3 = st.tabs(["High Severity Events", "Manufacturer and Brand Events", "Modality-specific Events"])
with tab1:
st.header("High Severity Events Across All Modalities")
limit_high_severity = st.number_input("Number of high severity events to retrieve:", min_value=1, max_value=100, value=10, key="high_severity_limit")
if st.button("Get High Severity Events"):
with st.spinner("Fetching high severity events..."):
high_severity_events = get_high_severity_events(limit_high_severity)
if high_severity_events:
data = []
for event in high_severity_events:
# Safely get brand_name and generic_name
device_info = event.get('device', [{}])[0]
brand_name = device_info.get('brand_name', 'Not specified')
generic_name = device_info.get('generic_name', 'Not specified')
# Ensure brand_name and generic_name are strings
brand_name = brand_name[0] if isinstance(brand_name, list) else brand_name
generic_name = generic_name[0] if isinstance(generic_name, list) else generic_name
data.append({
"Date of Event": safe_string(event.get('date_of_event', 'Not specified')),
"Product Problems": safe_string(', '.join(event.get('product_problems', ['Not specified']))),
"Event Type": safe_string(', '.join(event.get('event_type', ['Not specified']))),
"Brand Name": safe_string(brand_name),
"Generic Name": safe_string(generic_name)
})
df = pd.DataFrame(data)
gb = GridOptionsBuilder.from_dataframe(df)
gb.configure_pagination(paginationAutoPageSize=True)
gb.configure_side_bar()
gb.configure_default_column(groupable=True, value=True, enableRowGroup=True, aggFunc="sum", editable=True)
gridOptions = gb.build()
AgGrid(df, gridOptions=gridOptions, enable_enterprise_modules=True)
# Add download button for CSV
csv = df.to_csv(index=False)
st.download_button(
label="Download high severity events as CSV",
data=csv,
file_name="high_severity_events.csv",
mime="text/csv",
)
else:
st.warning("No high severity events found.")
with tab2:
st.header("Manufacturer and Brand Events")
# Fetch manufacturers with adverse events
manufacturers = get_manufacturer_events()
manufacturer_names = ["Select a manufacturer..."] + [item['term'] for item in manufacturers]
# Create manufacturer dropdown
selected_manufacturer = st.selectbox("Select manufacturer:", manufacturer_names)
limit = st.number_input("Number of events to retrieve:", min_value=1, max_value=1000, value=10, key="manufacturer_limit")
# Add severity filter
severity_options = ["All", "High", "Medium", "Low"]
selected_severity = st.selectbox("Filter by severity:", severity_options, key="manufacturer_severity")
if st.button("Get Manufacturer Events"):
if selected_manufacturer and selected_manufacturer != "Select a manufacturer...":
with st.spinner("Fetching manufacturer events..."):
events = get_manufacturer_details(selected_manufacturer, limit)
if 'results' in events and events['results']:
data = []
modalities = set()
for event in events['results']:
# Determine severity based on event type
severity = "Low"
event_types = event.get('event_type', [])
if "Death" in event_types:
severity = "High"
elif "Injury" in event_types or "Malfunction" in event_types:
severity = "Medium"
# Safely get brand_name and generic_name
device_info = event.get('device', [{}])[0]
brand_name = device_info.get('brand_name', 'Not specified')
generic_name = device_info.get('generic_name', 'Not specified')
# Ensure brand_name and generic_name are strings
brand_name = brand_name[0] if isinstance(brand_name, list) else brand_name
generic_name = generic_name[0] if isinstance(generic_name, list) else generic_name
modalities.add(generic_name)
data.append({
"Date of Event": safe_string(event.get('date_of_event', 'Not specified')),
"Brand Name": safe_string(brand_name),
"Generic Name (Modality)": safe_string(generic_name),
"Product Problems": safe_string(', '.join(event.get('product_problems', ['Not specified']))),
"Event Type": safe_string(', '.join(event_types)),
"Severity": safe_string(severity)
})
df = pd.DataFrame(data)
# Apply severity filter
if selected_severity != "All":
df = df[df["Severity"] == selected_severity]
# Add modality filter
modality_options = ["All"] + list(modalities)
selected_modality = st.selectbox("Filter by modality:", modality_options)
# Apply modality filter
if selected_modality != "All":
df = df[df["Generic Name (Modality)"] == selected_modality]
# Display the DataFrame using AgGrid
gb = GridOptionsBuilder.from_dataframe(df)
gb.configure_pagination(paginationAutoPageSize=True)
gb.configure_side_bar()
gb.configure_default_column(groupable=True, value=True, enableRowGroup=True, aggFunc="sum", editable=True)
gridOptions = gb.build()
AgGrid(df, gridOptions=gridOptions, enable_enterprise_modules=True)
# Add download button for CSV
csv = df.to_csv(index=False)
st.download_button(
label="Download manufacturer events as CSV",
data=csv,
file_name=f"{selected_manufacturer}_events.csv",
mime="text/csv",
)
else:
st.warning(f"No events found for the specified manufacturer.")
else:
st.warning("Please select a manufacturer.")
with tab3:
st.header("Modality-specific Events")
# Fetch and cache modalities with adverse events
modalities = get_modalities_with_events(100)
# Add a default option to the modalities list
modalities = ["Select a modality..."] + modalities
# Create modality dropdown
selected_modality = st.selectbox("Select modality:", modalities)
# Adjust the limit to respect API constraints
limit = st.number_input("Number of events to retrieve:", min_value=1, max_value=1000, value=10)
# Add severity filter
severity_options = ["All", "High", "Medium", "Low"]
selected_severity = st.selectbox("Filter by severity:", severity_options)
if st.button("Get Device Events"):
if selected_modality and selected_modality != "Select a modality...":
with st.spinner("Fetching device events..."):
events = get_device_events(selected_modality, limit)
if events and 'results' in events and events['results']:
data = []
for event in events['results']:
# Determine severity based on event type
severity = "Low"
event_types = event.get('event_type', [])
if "Death" in event_types:
severity = "High"
elif "Injury" in event_types or "Malfunction" in event_types:
severity = "Medium"
# Safely get brand_name and generic_name
device_info = event.get('device', [{}])[0]
brand_name = device_info.get('brand_name', 'Not specified')
generic_name = device_info.get('generic_name', 'Not specified')
# Ensure brand_name and generic_name are strings
brand_name = brand_name[0] if isinstance(brand_name, list) else brand_name
generic_name = generic_name[0] if isinstance(generic_name, list) else generic_name
data.append({
"Date of Event": safe_string(event.get('date_of_event', 'Not specified')),
"Product Problems": safe_string(', '.join(event.get('product_problems', ['Not specified']))),
"Event Type": safe_string(', '.join(event_types)),
"Severity": safe_string(severity),
"Brand Name": safe_string(brand_name),
"Generic Name": safe_string(generic_name)
})
df = pd.DataFrame(data)
# Apply severity filter
if selected_severity != "All":
df = df[df["Severity"] == selected_severity]
# Display the DataFrame using AgGrid
gb = GridOptionsBuilder.from_dataframe(df)
gb.configure_pagination(paginationAutoPageSize=True)
gb.configure_side_bar()
gb.configure_default_column(groupable=True, value=True, enableRowGroup=True, aggFunc="sum", editable=True)
gridOptions = gb.build()
AgGrid(df, gridOptions=gridOptions, enable_enterprise_modules=True)
# Add download button for CSV
csv = df.to_csv(index=False)
st.download_button(
label="Download data as CSV",
data=csv,
file_name=f"{selected_modality}_events_filtered.csv",
mime="text/csv",
)
else:
st.warning(f"No events found for the specified modality or an error occurred.")
else:
st.warning("Please select a modality.")
# Add footer with API information
st.markdown("---")
st.markdown("Data provided by the [FDA Adverse Event Reporting System API](https://open.fda.gov/apis/device/event/)")
# Add developer credit and Buy Me a Coffee link
st.markdown("Developed with ❤️ by [Ryan](https://github.com/skidad75) | [Buy Me a Coffee](https://buymeacoffee.com/skidad75)")