import json
-for line inopen(jsonfile):
+for line inopen(jsonfile):
line = f.readline()
然后再解析json
import dateutil.parser
@@ -1940,23 +1964,23 @@ date = dateutil.parser.parse(lin["
dataarray = []
datacount =0
- for line inopen(jsonfile):
+ for line inopen(jsonfile):
line = f.readline()
lin = json.loads(line)
date = dateutil.parser.parse(lin["created_at"])
datacount +=1
dataarray.append(date.minute)
- minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
+ minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
f.close()
return minuteswithcount
下面这句代码就是将上面的解析为
-
minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
+
minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
@@ -1982,14 +2006,14 @@ date = dateutil.parser.parse(lin["
dataarray = []
datacount =0
- for line inopen(jsonfile):
+ for line inopen(jsonfile):
line = f.readline()
lin = json.loads(line)
date = dateutil.parser.parse(lin["created_at"])
datacount +=1
dataarray.append(date.minute)
- minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
+ minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
f.close()
return minuteswithcount
@@ -1998,7 +2022,7 @@ date = dateutil.parser.parse(lin["
x = []
y = []
mwcs = parse_data(files)
- for mwc in mwcs:
+ for mwc in mwcs:
x.append(mwc[0])
y.append(mwc[1])
@@ -2052,7 +2076,7 @@ draw_date("data/2014-01-01-0.json")重写了一个新的方法用于计算提交数，直至后面才意识到其实我们可以算行数就够了，但是方法上有点hack
def get_minutes_counts_with_id(jsonfile):
datacount, dataarray = handle_json(jsonfile)
- minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
+ minuteswithcount = [(x, dataarray.count(x)) for x inset(dataarray)]
return minuteswithcount
@@ -2061,7 +2085,7 @@ draw_date("data/2014-01-01-0.json")= []
datacount =0
- for line inopen(jsonfile):
+ for line inopen(jsonfile):
line = f.readline()
lin = json.loads(line)
date = dateutil.parser.parse(lin["created_at"])
@@ -2083,7 +2107,7 @@ draw_date("data/2014-01-01-0.json") :rtype : object
"""
monthdaycount = []
- for i inrange(1, 20):
+ for i inrange(1, 20):
if i <10:
filename ='data/2014-02-0'+ i.__str__() +'-0.json'else:
@@ -2118,43 +2142,43 @@ draw_date("data/2014-01-01-0.json")= 0
userinfo = []
condition ='select * from userinfo where owener = \''+str(username) +'\''
- for zero in c.execute(condition):
+ for zero in c.execute(condition):
count +=1
userinfo.append(zero)
return count, userinfo
def handle_gzip_file(filename):
userinfo = []
with gzip.GzipFile(filename) as f:
- events = [line.decode("utf-8", errors="ignore") for line in f]
+ events = [line.decode("utf-8", errors="ignore") for line in f]
- for n, line inenumerate(events):
+ for n, line inenumerate(events):
try:
event = json.loads(line)
except:
@@ -2163,7 +2187,7 @@ draw_date("data/2014-01-01-0.json")= event["actor"]
attrs = event.get("actor_attributes", {})
- if actor isNoneor attrs.get("type") !="User":
+ if actor isNoneor attrs.get("type") !="User":
continue
key = actor.lower()
@@ -2183,7 +2207,7 @@ draw_date("data/2014-01-01-0.json")= 2014
month =3
- for day inrange(1,31):
+ for day inrange(1,31):
date_re = re.compile(r"([0-9]{4})-([0-9]{2})-([0-9]{2})-([0-9]+)\.json.gz")
fn_template = os.path.join("march",
@@ -2191,7 +2215,7 @@ draw_date("data/2014-01-01-0.json")= {"year": year, "month": month, "day": day, "n": "*"}
filenames = glob.glob(fn_template.format(**kwargs))
- for filename in filenames:
+ for filename in filenames:
c.executemany('INSERT INTO userinfo VALUES (?,?,?,?,?)', handle_gzip_file(filename))
conn.commit()
@@ -2217,11 +2241,11 @@ pipe = pipe = r.pipeline()
pipe.zscore('osrc:user',"gmszone")
pipe.execute()
系统返回了227.0,试试别人。
-
>>>pipe.zscore('osrc:user',"dfm")
-<redis.client.StrictPipeline object at 0x104fa7f50>
->>>pipe.execute()
-[425.0]
->>>
+
>>>pipe.zscore('osrc:user',"dfm")
+<redis.client.StrictPipeline object at 0x104fa7f50>
+>>>pipe.execute()
+[425.0]
+>>>
r = redis.StrictRedis(host='localhost', port=6379, db=0)
no_pipe =False
- if pipe isNone:
+ if pipe isNone:
pipe = pipe = r.pipeline()
no_pipe =True
@@ -2304,12 +2328,12 @@ pipe.execute()
points[0] =1.0/ (total +1)
# Week means.
- for k, v in results[1].iteritems():
+ for k, v in results[1].iteritems():
points[1+int(k)] =float(v) / total
# Event types.
n =8
- for k, v in results[2]:
+ for k, v in results[2]:
points[n + evttypes.index(k)] =float(v) / total
# Number of contributions, connections and languages.
@@ -2321,8 +2345,8 @@ pipe.execute()
# Top languages.
n +=4
- for k, v in results[7]:
- if k in langs:
+ for k, v in results[7]:
+ if k in langs:
points[n + langs.index(k)] =float(v) / total
else:
# Unknown language.
@@ -2989,5 +3013,11 @@ pipe.execute()
