"「知恵袋」あり": defaultdict(lambda: 0),
"「知恵袋」なし": defaultdict(lambda: 0)
}
img_rexp = re.compile(r'.*%s.*' % "画像")
video_rexp = re.compile(r'.*%s.*' % "動画")
map_rexp = re.compile(r'.*%s.*' % "地図")
chie_rexp = re.compile(r'.*%s.*' % "知恵袋")
news_rexp = re.compile(r'.*%s.*' % "ニュース")
recipe_rexp = [re.compile(r'.*%s.*' % "クックパッド"), re.compile(r'.*%s.*' % "レシピ")]
for fileNum in xrange(2,9):
# for line in open('../data/2015110'+str(fileNum)+'_all', 'r'):
for line in open('../data/small_data.txt', 'r'):
featureArray = line.split("\t")
# if featureArray[11] == "":
# continue
if cm.typical_vertical(featureArray[10]) == "image":
if img_rexp.match(featureArray[7]):
result["「画像」あり"][featureArray[10]] += 1
result["「画像」あり"]["all"] += 1
else:
result["「画像」なし"][featureArray[10]] += 1
result["「画像」なし"]["all"] += 1
elif cm.typical_vertical(featureArray[10]) == "recipe":
if recipe_rexp[0].match(featureArray[7]) or recipe_rexp[1].match(featureArray[7]):
result["「レシピ」あり"][featureArray[10]] += 1
result["「レシピ」あり"]["all"] += 1
else:
result["「レシピ」なし"][featureArray[10]] += 1
result["「レシピ」なし"]["all"] += 1
elif cm.typical_vertical(featureArray[10]) == "video":
if video_rexp[0].match(featureArray[7]):
},
}
outputs = {
"device": {},
"gender": {},
"generation": {}
}
other_verical_array = []
for fileNum in xrange(2,9):
for line in open('../data/2015110'+str(fileNum)+'_all', 'r'):
# for line in open('../data/small_data.txt', 'r'):
featureArray = line.split("\t")
vertical = cm.typical_vertical(featureArray[10])
if vertical != "video":
continue
device = featureArray[8]
if vertical == "other" and featureArray[10] not in other_verical_array:
other_verical_array.append(featureArray[10])
birthYear = featureArray[2]
gender = featureArray[1]
# vertical = "None"
allDict["all"]["all"] += 1
if birthYear != "" and gender != "" and device in ["smartphone", "tablet", "pc", "tv", "featurephone"]:
generation = cm.generation_distinction(birthYear)
generationDict[generation]["all"] += 1
generationDict[generation][vertical] += 1
genderDict[gender]["all"] += 1
if __name__ == "__main__":
result = {
"「画像」あり": defaultdict(lambda: 0),
"「画像」なし": defaultdict(lambda: 0),
"「レシピ」あり": defaultdict(lambda: 0),
"「レシピ」なし": defaultdict(lambda: 0)
}
img_rexp = re.compile(r'.*%s.*' % "画像")
recipe_rexp = [re.compile(r'.*%s.*' % "クックパッド"), re.compile(r'.*%s.*' % "レシピ")]
for fileNum in xrange(2,9):
# for line in open('../data/2015110'+str(fileNum)+'_all', 'r'):
for line in open('../data/small_data.txt', 'r'):
featureArray = line.split("\t")
# if featureArray[11] == "":
# continue
if cm.typical_vertical(featureArray[10]) == "image":
if img_rexp.match(featureArray[7]):
result["「画像」あり"][featureArray[10]] += 1
result["「画像」あり"]["all"] += 1
else:
result["「画像」なし"][featureArray[10]] += 1
result["「画像」なし"]["all"] += 1
elif cm.typical_vertical(featureArray[10]) == "recipe":
if recipe_rexp[0].match(featureArray[7]) or recipe_rexp[1].match(featureArray[7]):
result["「レシピ」あり"][featureArray[10]] += 1
result["「レシピ」あり"]["all"] += 1
else:
result["「レシピ」なし"][featureArray[10]] += 1
result["「レシピ」なし"]["all"] += 1
print_dict_content(result)
