Added metadata, and metadata import script.

test_data/import.py

+from pymongo import MongoClient
+import argparse
+import json
+import sys
+
+def progress(current, end):
+	percent = float(current) / end
+	hashes = "#" * int(round(percent * 20))
+	spaces = " " * (20 - len(hashes))
+	sys.stdout.write("\rProcessed %s / %s entries. [%s] %s%%" % (current, end, hashes + spaces, int(round(percent * 100))))
+	sys.stdout.flush()
+
+parser = argparse.ArgumentParser(description = "Import all test data into the database.")
+parser.add_argument("--password", dest="password", required=True, help="Database user password.")
+parser.add_argument("--username", dest="username", default="aknecht", required=True, help="Database user.")
+parser.add_argument("--host", dest="host", default="hcc-anvil-241-41.unl.edu", required=True, help="Database host.")
+parser.add_argument("--drop", dest="drop", default=False, action="store_true", help="Drop data if it exists.")
+args = parser.parse_args()
+
+# Everything in a db named chipseq 
+# Set up connection and authenticate
+
+client = MongoClient(args.host)
+db = client.chipseq
+db.authenticate(args.username, args.password, mechanism="SCRAM-SHA-1")
+
+if args.drop:
+	db.experiments.drop()
+	db.samples.drop()
+
+# Insert all experiment metadata, expected in meta/meta_clean.json
+with open("meta/meta_clean.json", "r") as rh:
+	data = json.load(rh)
+	exp_ids = db.experiments.insert_many(data)
+
+organism = {
+	"mm": "mouse",
+	"hg": "human",
+	"ce": "celegans"
+}
+
+# Loop through experiments to create samples
+cursor = db.experiments.find({
+	"target": {"$exists": True}, 
+	"revoked_files.0": {"$exists": False}, 
+	"assembly.0": {"$exists": True}, 
+	"assembly.1": {"$exists": False}
+})
+
+total = cursor.count()
+
+for i,document in enumerate(cursor):
+	for f in document["files"]:
+		doc = {}
+		doc["experiment_id"] = document["_id"]
+		doc["organism"] = organism[document["assembly"][0][:2]]
+		doc["genome"] = document["assembly"][0]
+		if "/targets/H" in document["target"]:
+			doc["histone_modification"] = document["target"].split("/")[2][:2]
+			doc["transcription_factor"] = document["target"].split("/")[2][2:].split("-")[0]
+		else:
+			doc["transcription_factor"] = document["target"].split("/")[2].split("-")[0]
+		doc["cell_type"] = document["biosample_term_name"]
+		doc["url"] = "encodeproject.org%s@@download" % (f,)
+		db.samples.insert_one(doc)
+	progress(i, total)
+
+progress(total, total)
+print
+