Updated import script, fixed progress utility.

chipathlon/utils.py

@@ -5,5 +5,4 @@ def progress(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()

meta/import.py

@@ -11,7 +11,7 @@ parser.add_argument("--host", dest="host", default="hcc-anvil-241-41.unl.edu", r
 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 
+# Everything in a db named chipseq
 # Set up connection and authenticate
 
 client = MongoClient(args.host)
@@ -35,9 +35,9 @@ organism = {
 
 # Loop through experiments to create samples
 cursor = db.experiments.find({
-	"target": {"$exists": True}, 
-	"revoked_files.0": {"$exists": False}, 
-	"assembly.0": {"$exists": True}, 
+	"target": {"$exists": True},
+	"revoked_files.0": {"$exists": False},
+	"assembly.0": {"$exists": True},
 	"assembly.1": {"$exists": False}
 })
 
@@ -52,6 +52,8 @@ for i,document in enumerate(cursor):
 		if "/targets/H" in document["target"]:
 			doc["histone_modification"] = document["target"].split("/")[2][:2]
 			doc["transcription_factor"] = document["target"].split("/")[2][2:].split("-")[0]
+		elif document["target"].split("/")[2].split("-")[0].lower() == "control":
+			doc["control"] = True
 		else:
 			doc["transcription_factor"] = document["target"].split("/")[2].split("-")[0]
 		doc["cell_type"] = document["biosample_term_name"]
@@ -61,4 +63,3 @@ for i,document in enumerate(cursor):
 
 progress(total, total)
 print
-