Fda Database

pip install requests pandas

import requests

BASE = "https://api.fda.gov/drug"
# Optional: add api_key parameter for higher rate limits

# Find adverse events for aspirin
r = requests.get(
    f"{BASE}/event.json",
    params={
        "search": 'patient.drug.medicinalproduct:"aspirin"',
        "count": "patient.reaction.reactionmeddrapt.exact",
        "limit": 10
    }
)
r.raise_for_status()
data = r.json()
print("Top adverse reactions for aspirin:")
for item in data["results"][:5]:
    print(f"  {item['term']:40s} count={item['count']}")

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def faers_search(drug_name, limit=100):
    """Search FAERS for adverse event reports mentioning a drug."""
    r = requests.get(f"{BASE}/event.json",
                     params={"search": f'patient.drug.medicinalproduct:"{drug_name}"',
                             "limit": limit})
    r.raise_for_status()
    return r.json()

data = faers_search("warfarin", limit=5)
total = data["meta"]["results"]["total"]
print(f"Total FAERS reports for warfarin: {total:,}")

# Show first report summary
report = data["results"][0]
print(f"\nReport {report['safetyreportid']}:")
print(f"  Date     : {report.get('receivedate', 'n/a')}")
print(f"  Serious  : {report.get('serious', 'n/a')}")
drugs = [d.get("medicinalproduct", "n/a") for d in report.get("patient", {}).get("drug", [])]
print(f"  Drugs    : {drugs[:5]}")
reactions = [r.get("reactionmeddrapt", "n/a") for r in report.get("patient", {}).get("reaction", [])]
print(f"  Reactions: {reactions[:5]}")

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def top_adverse_events(drug_name, limit=20):
    """Get the most frequently reported adverse events for a drug."""
    r = requests.get(f"{BASE}/event.json",
                     params={
                         "search": f'patient.drug.medicinalproduct:"{drug_name}"',
                         "count": "patient.reaction.reactionmeddrapt.exact",
                         "limit": limit
                     })
    r.raise_for_status()
    results = r.json()["results"]
    return pd.DataFrame(results).rename(columns={"term": "reaction", "count": "reports"})

df_atorvastatin = top_adverse_events("atorvastatin", limit=15)
print("Top adverse events for atorvastatin:")
print(df_atorvastatin.head(10).to_string(index=False))
df_atorvastatin.to_csv("atorvastatin_adverse_events.csv", index=False)

# Compare two drugs: adverse event profile overlap
df_drug1 = top_adverse_events("simvastatin", limit=20)
df_drug2 = top_adverse_events("atorvastatin", limit=20)

common = set(df_drug1["reaction"]) & set(df_drug2["reaction"])
print(f"\nCommon adverse events (simvastatin ∩ atorvastatin): {len(common)}")
print("Shared reactions:", list(common)[:10])

import requests

BASE = "https://api.fda.gov/drug"

def get_label(drug_name):
    """Retrieve FDA drug label by brand or generic name."""
    r = requests.get(f"{BASE}/label.json",
                     params={"search": f'openfda.brand_name:"{drug_name}"',
                             "limit": 1})
    if r.status_code == 404:
        r = requests.get(f"{BASE}/label.json",
                         params={"search": f'openfda.generic_name:"{drug_name}"',
                                 "limit": 1})
    r.raise_for_status()
    results = r.json()["results"]
    return results[0] if results else None

label = get_label("Lipitor")
if label:
    print(f"Brand name  : {label.get('openfda', {}).get('brand_name', ['n/a'])[0]}")
    print(f"Generic name: {label.get('openfda', {}).get('generic_name', ['n/a'])[0]}")
    print(f"Manufacturer: {label.get('openfda', {}).get('manufacturer_name', ['n/a'])[0]}")
    indications = label.get("indications_and_usage", ["n/a"])[0]
    print(f"\nIndications (first 300 chars):\n{indications[:300]}...")

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def ndc_search(ndc_or_name, limit=10):
    """Search NDC directory for drug product information."""
    # Search by product name or NDC
    r = requests.get(f"{BASE}/ndc.json",
                     params={"search": f'generic_name:"{ndc_or_name}"',
                             "limit": limit})
    r.raise_for_status()
    return r.json()

data = ndc_search("metformin", limit=10)
total = data["meta"]["results"]["total"]
print(f"Metformin products: {total}")

rows = []
for prod in data["results"]:
    rows.append({
        "product_ndc": prod.get("product_ndc"),
        "brand_name": prod.get("brand_name"),
        "generic_name": prod.get("generic_name"),
        "dosage_form": prod.get("dosage_form"),
        "route": ", ".join(prod.get("route", [])),
        "labeler": prod.get("labeler_name"),
    })
df = pd.DataFrame(rows)
print(df.to_string(index=False))

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def drug_recalls(drug_name, limit=20):
    """Find FDA drug recalls for a given drug name."""
    r = requests.get(f"{BASE}/enforcement.json",
                     params={
                         "search": f'product_description:"{drug_name}"',
                         "limit": limit
                     })
    if r.status_code == 404:
        return pd.DataFrame()
    r.raise_for_status()
    results = r.json()["results"]
    return pd.DataFrame([{
        "recalling_firm": rec.get("recalling_firm"),
        "product": rec.get("product_description", "")[:80],
        "reason": rec.get("reason_for_recall", "")[:100],
        "classification": rec.get("classification"),
        "recall_date": rec.get("recall_initiation_date"),
        "status": rec.get("status"),
    } for rec in results])

recalls = drug_recalls("metformin", limit=5)
print(f"Metformin recalls: {len(recalls)}")
if not recalls.empty:
    print(recalls[["recalling_firm", "classification", "recall_date", "status"]].to_string(index=False))

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def products_by_ingredient(ingredient, limit=50):
    """Find all FDA-listed products with a given active ingredient."""
    r = requests.get(f"{BASE}/ndc.json",
                     params={
                         "search": f'active_ingredients.name:"{ingredient}"',
                         "limit": limit
                     })
    r.raise_for_status()
    data = r.json()
    print(f"Total products with {ingredient}: {data['meta']['results']['total']}")

    rows = []
    for prod in data["results"]:
        for ai in prod.get("active_ingredients", []):
            if ingredient.lower() in ai.get("name", "").lower():
                rows.append({
                    "brand": prod.get("brand_name"),
                    "generic": prod.get("generic_name"),
                    "strength": ai.get("strength"),
                    "dosage_form": prod.get("dosage_form"),
                    "route": ", ".join(prod.get("route", [])),
                })
    return pd.DataFrame(rows)

df = products_by_ingredient("metformin hydrochloride")
print(df.drop_duplicates(subset=["generic", "strength", "dosage_form"]).head(10).to_string(index=False))

import requests, pandas as pd, time

BASE = "https://api.fda.gov/drug"

drugs = ["atorvastatin", "simvastatin", "rosuvastatin"]

def count_reactions(drug, limit=20):
    r = requests.get(f"{BASE}/event.json",
                     params={"search": f'patient.drug.medicinalproduct:"{drug}"',
                             "count": "patient.reaction.reactionmeddrapt.exact",
                             "limit": limit})
    if r.status_code != 200:
        return pd.Series(dtype=float, name=drug)
    df = pd.DataFrame(r.json()["results"])
    df.columns = ["reaction", drug]
    return df.set_index("reaction")[drug]

series_list = []
for drug in drugs:
    s = count_reactions(drug, limit=20)
    series_list.append(s)
    time.sleep(0.5)

comparison = pd.concat(series_list, axis=1).fillna(0)
comparison = comparison.sort_values(drugs[0], ascending=False)
print("Adverse event count comparison (statins):")
print(comparison.head(10).to_string())
comparison.to_csv("statin_safety_comparison.csv")

import requests, pandas as pd, time, re

BASE = "https://api.fda.gov/drug"

def get_label_sections(drug_name):
    r = requests.get(f"{BASE}/label.json",
                     params={"search": f'openfda.generic_name:"{drug_name}"', "limit": 1})
    if r.status_code != 200 or not r.json()["results"]:
        return None
    label = r.json()["results"][0]

    def clean(field):
        text = " ".join(label.get(field, [""]))
        return re.sub(r"\s+", " ", text).strip()[:500]

    return {
        "drug": drug_name,
        "indications": clean("indications_and_usage"),
        "contraindications": clean("contraindications"),
        "warnings": clean("warnings_and_cautions") or clean("warnings"),
    }

drugs = ["metformin", "atorvastatin", "lisinopril", "omeprazole"]
rows = []
for drug in drugs:
    info = get_label_sections(drug)
    if info:
        rows.append(info)
    time.sleep(0.4)

df = pd.DataFrame(rows)
df.to_csv("drug_labels.csv", index=False)
print(df[["drug", "indications"]].to_string(index=False))