当前位置: 首页>>代码示例>>Python>>正文


Python es_flow_text.search函数代码示例

本文整理汇总了Python中user_portrait.global_utils.es_flow_text.search函数的典型用法代码示例。如果您正苦于以下问题:Python search函数的具体用法?Python search怎么用?Python search使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。


在下文中一共展示了search函数的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: query_hot_mid

def query_hot_mid(ts, keywords_list, text_type,size=100):
    query_body = {
        "query":{
            "filtered":{
                "filter":{
                    "bool":{
                        "must":[
                            {"range":{
                                "timestamp":{
                                    "gte":ts - time_interval,
                                    "lt": ts
                                }
                            }},
                            {"terms": {"keywords_string": keywords_list}},
                            {"term": {"message_type": "0"}}
                        ]
                    }
                }
            }
        },
        "aggs":{
            "all_interests":{
                "terms":{"field": "root_mid", "size": size}
            }
        }
    }

    datetime = ts2datetime(ts)
    datetime_1 = ts2datetime(ts-time_interval)
    index_name = flow_text_index_name_pre + datetime
    exist_es = es_text.indices.exists(index_name)
    index_name_1 = flow_text_index_name_pre + datetime_1
    exist_bool_1 = es_text.indices.exists(index_name_1)
    print datetime, datetime_1
    if datetime == datetime_1 and exist_es:
        search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["aggregations"]["all_interests"]["buckets"]
    elif datetime != datetime_1 and exist_bool_1:
        search_results = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body)["aggregations"]["all_interests"]["buckets"]
    else:
        search_results = []

    hot_mid_list = []
    if search_results:
        for item in search_results:
            print item
            temp = []
            temp.append(item['key'])
            temp.append(item['doc_count'])
            hot_mid_list.append(temp)

    #print hot_mid_list

    return hot_mid_list
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:53,代码来源:full_text_serach.py

示例2: query_mid_list

def query_mid_list(ts, keywords_list, time_segment, social_sensors=[]):
    query_body = {
        "query": {
            "filtered": {
                "filter": {
                    "bool": {
                        "must": [
                            {"range": {
                                "timestamp": {
                                    "gte": ts - time_segment,
                                    "lt": ts
                                 }
                            }},
                            {"terms": {"keywords_string": keywords_list}}
                        ]
                    }
                }
            }
        },
        "size": 10000
    }

    if social_sensors:
        query_body['query']['filtered']['filter']['bool']['must'].append({"terms": {"uid": social_sensors}})

    datetime = ts2datetime(ts)
    index_name = flow_text_index_name_pre + datetime
    exist_es = es_text.indices.exists(index_name)
    if exist_es:
        search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body, fields=["root_mid"])["hits"]["hits"]
    else:
        search_results = []
    origin_mid_list = set() # all related weibo mid list
    if search_results:
        for item in search_results:
            #if item.get("fields", ""):
            #    origin_mid_list.append(item["fields"]["root_mid"][0])
            #else:
            origin_mid_list.add(item["_id"])

    datetime_1 = ts2datetime(ts-time_segment)
    index_name_1 = flow_text_index_name_pre + datetime_1
    exist_bool = es_text.indices.exists(index_name_1)
    if datetime != datetime_1 and exist_bool:
        search_results_1 = es_text.search(index=index_name_1, doc_type=flow_text_index_type, body=query_body, fields=['root_mid'])["hits"]["hits"]
        if search_results_1:
            for item in search_results_1:
                #if item.get("fields", ""):
                #    origin_mid_list.append(item["fields"]["root_mid"][0])
                #else:
                origin_mid_list.add(item["_id"])

    return list(origin_mid_list)
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:53,代码来源:full_text_serach.py

示例3: search_group_sentiment_weibo

def search_group_sentiment_weibo(task_name, start_ts, sentiment):
    weibo_list = []
    #step1:get task_name uid
    try:
        group_result = es_group_result.get(index=group_index_name, doc_type=group_index_type,\
                        id=task_name, _source=False, fields=['uid_list'])
    except:
        group_result = {}
    if group_result == {}:
        return 'task name invalid'
    try:
        uid_list = group_result['fields']['uid_list']
    except:
        uid_list = []
    if uid_list == []:
        return 'task uid list null'
    #step3: get ui2uname
    uid2uname = {}
    try:
        user_portrait_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type,\
                        body={'ids':uid_list}, _source=False, fields=['uname'])['docs']
    except:
        user_portrait_result = []
    for item in user_portrait_result:
        uid = item['_id']
        if item['found']==True:
            uname = item['fields']['uname'][0]
            uid2uname[uid] = uname
    #step4:iter date to search weibo
    weibo_list = []
    iter_date = ts2datetime(start_ts)
    flow_text_index_name = flow_text_index_name_pre + str(iter_date)
    #step4: get query_body
    if sentiment != '2':
        query_body = [{'terms': {'uid': uid_list}}, {'term':{'sentiment': sentiment}}, \
                {'range':{'timestamp':{'gte':start_ts, 'lt': start_ts+DAY}}}]
    else:
        query_body = [{'terms':{'uid':uid_list}}, {'terms':{'sentiment': SENTIMENT_SECOND}},\
                {'range':{'timestamp':{'gte':start_ts, 'lt':start_ts+DAY}}}]
    try:
        flow_text_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                body={'query':{'bool':{'must': query_body}}, 'sort': [{'timestamp':{'order':'asc'}}], 'size': MAX_VALUE})['hits']['hits']
    except:
        flow_text_result = []
    for flow_text_item in flow_text_result:
        source = flow_text_item['_source']
        weibo = {}
        weibo['uid'] = source['uid']
        weibo['uname'] = uid2uname[weibo['uid']]
        weibo['ip'] = source['ip']
        try:
            weibo['geo'] = '\t'.join(source['geo'].split('&'))
        except:
            weibo['geo'] = ''
        weibo['text'] = source['text']
        weibo['timestamp'] = source['timestamp']
        weibo['sentiment'] = source['sentiment']
        weibo_list.append(weibo)

    return weibo_list
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:60,代码来源:utils.py

示例4: get_repost_weibo

def get_repost_weibo(mid, weibo_timestamp):
    repost_result = []
    index_date = ts2datetime(weibo_timestamp)
    index_name = flow_text_index_name_pre + index_date
    query_body = {
            'query':{
                'bool':{
                    'must':[
                        {'term':{'root_mid': mid}},
                        {'range':{'timestamp':{'gte': weibo_timestamp}}},
                        {'term':{'message_type': 2}}
                        ]
                    }
                }
            }
    try:
        flow_text_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
                body=query_body)['hits']['hits']
    except:
        flow_text_result = []
    repost_uid_list = [item['_source']['uid'] for item in flow_text_result]
    repost_user_info_dict = get_user_profile_weibo(repost_uid_list)
    statuses = []
    for item in flow_text_result:
        item_source = item['_source']
        item_source['user'] = repost_user_info_dict[item['uid']]
        statuses.append(item_source)
    
    return statuses
开发者ID:huxiaoqian,项目名称:revised_user_portrait,代码行数:29,代码来源:new_search.py

示例5: get_psycho_status

def get_psycho_status(uid_list):
    results = {}
    uid_sentiment_dict = {}
    #time for es_flow_text
    now_ts = time.time()
    now_date_ts = datetime2ts(ts2datetime(now_ts))
    #run_type
    if RUN_TYPE == 0:
        now_date_ts = datetime2ts(RUN_TEST_TIME)
    start_date_ts = now_date_ts - DAY * WEEK
    for i in range(0, WEEK):
        iter_date_ts = start_date_ts + DAY * i
        flow_text_index_date = ts2datetime(iter_date_ts)
        flow_text_index_name = flow_text_index_name_pre + flow_text_index_date
        try:
            flow_text_exist = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body={'query':{'filtered':{'filter':{'terms':{'uid': uid_list}}}}, 'size': MAX_VALUE}, _source=False,  fields=['uid', 'sentiment'])['hits']['hits']
        except:
            flow_text_exist = []
        for flow_text_item in flow_text_exist:
            uid = flow_text_item['fields']['uid'][0]
            sentiment = flow_text_item['fields']['sentiment'][0]
            if uid in uid_sentiment_dict:
                try:
                    uid_sentiment_dict[uid][str(sentiment)] += 1
                except:
                    uid_sentiment_dict[uid][str(sentiment)] = 1
            else:
                uid_sentiment_dict[uid] = {str(sentiment): 1}
    #compute first and second psycho_status
    for uid in uid_list:
        results[uid] = {'first':{}, 'second':{}}
        try:
            user_sentiment_result = uid_sentiment_dict[uid]
        except:
            user_sentiment_result = {}
        all_count = sum(user_sentiment_result.values())
        #compute second level sentiment---negative type sentiment
        second_sentiment_count_list = [user_sentiment_result[item] for item in user_sentiment_result if item in SENTIMENT_SECOND]
        second_sentiment_all_count = sum(second_sentiment_count_list)
        for sentiment_item in SENTIMENT_SECOND:
            try:
                results[uid]['second'][sentiment_item] = float(user_sentiment_result[sentiment_item]) / all_count
            except:
                results[uid]['second'][sentiment_item] = 0
        #compute first level sentiment---middle, postive, negative
        user_sentiment_result['7'] = second_sentiment_all_count
        for sentiment_item in SENTIMENT_FIRST:
            try:
                sentiment_ratio = float(user_sentiment_result[sentiment_item]) / all_count
            except:
                sentiment_ratio = 0
            results[uid]['first'][sentiment_item] = sentiment_ratio

    return results
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:55,代码来源:utils.py

示例6: get_activity_weibo

def get_activity_weibo(task_name, start_ts):
    results = []
    #step1: get task_name uid
    try:
        group_result = es_group_result.get(index=group_index_name, doc_type=group_index_type ,\
                id=task_name, _source=False, fields=['uid_list'])
    except:
        group_result = {}
    if group_result == {}:
        return 'task name invalid'
    try:
        uid_list = group_result['fields']['uid_list']
    except:
        uid_list = []
    if uid_list == []:
        return 'task uid list null'
    #step2: get uid2uname
    uid2uname = {}
    try:
        user_portrait_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
                body = {'ids':uid_list}, _source=False, fields=['uname'])['docs']
    except:
        user_portrait_result = []
    for item in user_portrait_result:
        uid = item['_id']
        if item['found']==True:
            uname = item['fields']['uname'][0]
        uid2uname[uid] = uname
    #step3: search time_segment weibo
    time_segment = FOUR_HOUR
    end_ts = start_ts + time_segment
    time_date = ts2datetime(start_ts)
    flow_text_index_name = flow_text_index_name_pre + time_date
    query = []
    query.append({'terms':{'uid': uid_list}})
    query.append({'range':{'timestamp':{'gte':start_ts, 'lt':end_ts}}})
    try:
        flow_text_es_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type, \
                body={'query':{'bool':{'must':query}}, 'sort':'timestamp', 'size':MAX_VALUE})['hits']['hits']
    except:
        flow_text_es_result = []
    for item in flow_text_es_result:
        weibo = {}
        source = item['_source']
        weibo['timestamp'] = ts2date(source['timestamp'])
        weibo['ip'] = source['ip']
        weibo['text'] = source['text']
        if source['geo']:
            weibo['geo'] = '\t'.join(source['geo'])
        else:
            weibo['geo'] = ''
        results.append(weibo)

    return results
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:54,代码来源:utils.py

示例7: new_get_user_weibo

def new_get_user_weibo(uid, sort_type):
    results = []
    weibo_list = []
    now_date = ts2datetime(time.time())
    #run_type
    if RUN_TYPE == 0:
        now_date = RUN_TEST_TIME
        sort_type = 'timestamp'
    #step1:get user name
    try:
        user_profile_result = es_user_profile.get(index=profile_index_name, doc_type=profile_index_type,\
                id=uid, _source=False, fields=['nick_name'])
    except:
        user_profile_result = {}
    if user_profile_result:
        uname = user_profile_result['fields']['nick_name'][0]
    else:
        uname = ''
    #step2:get user weibo
    for i in range(7, 0, -1):
        iter_date = ts2datetime(datetime2ts(now_date) - i * DAY)
        index_name = flow_text_index_name_pre + iter_date
        try:
            weibo_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
                    body={'query':{'filtered':{'filter':{'term': {'uid': uid}}}}, 'sort':sort_type, 'size':100})['hits']['hits']
        except:
            weibo_result = []
        if weibo_result:
            weibo_list.extend(weibo_result)
    print 'weibo_list:', weibo_list[0]
    sort_weibo_list = sorted(weibo_list, key=lambda x:x['_source'][sort_type], reverse=True)[:100]
    for weibo_item in sort_weibo_list:
        source = weibo_item['_source']
        mid = source['mid']
        uid = source['uid']
        text = source['text']
        ip = source['geo']
        timestamp = source['timestamp']
        date = ts2date(timestamp)
        sentiment = source['sentiment']
        #run_type
        if RUN_TYPE == 1:
            retweet_count = source['retweet_count']
            comment_count = source['comment_count']
            sensitive_score = source['sensitive']
        else:
            retweet_count = 0
            comment_count = 0
            sensitive_score = 0
        city = ip2city(ip)
        results.append([mid, uid, text, ip, city,timestamp, date, retweet_count, comment_count, sensitive_score])

    return results
开发者ID:huxiaoqian,项目名称:revised_user_portrait,代码行数:53,代码来源:new_search.py

示例8: get_social_inter_content

def get_social_inter_content(uid1, uid2, type_mark):
    weibo_list = []
    #get two type relation about uid1 and uid2
    #search weibo list
    now_ts = int(time.time())
    #run_type
    if RUN_TYPE == 1:
        now_date_ts = datetime2ts(ts2datetime(now_ts))
    else:
        now_date_ts = datetime2ts(RUN_TEST_TIME)
    #uid2uname
    uid2uname = {}
    try:
        portrait_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type ,\
                                body={'ids': [uid1, uid2]}, _source=False, fields=['uid', 'uname'])['docs']
    except:
        portrait_result = []
    
    for item in portrait_result:
        uid = item['_id']
        if item['found'] == True:
            uname = item['fields']['uname'][0]
            uid2uname[uid] = uname
        else:
            uid2uname[uid] = 'unknown'
    #iter date to search weibo list
    for i in range(7, 0, -1):
        iter_date_ts = now_date_ts - i*DAY
        iter_date = ts2datetime(iter_date_ts)
        flow_text_index_name = flow_text_index_name_pre + str(iter_date)
        query = []
        query.append({'bool':{'must':[{'term':{'uid':uid1}}, {'term':{'directed_uid': int(uid2)}}]}})
        if type_mark=='out':
            query.append({'bool':{'must':[{'term':{'uid':uid2}}, {'term':{'directed_uid': int(uid1)}}]}})
        try:
            flow_text_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body={'query': {'bool':{'should': query}}, 'sort':[{'timestamp':{'order': 'asc'}}], 'size':MAX_VALUE})['hits']['hits']
        except:
            flow_text_result = []
        for flow_text in flow_text_result:
            source = flow_text['_source']
            weibo = {}
            weibo['timestamp'] = source['timestamp']
            weibo['ip'] = source['ip']
            weibo['geo'] = source['geo']
            weibo['text'] = '\t'.join(source['text'].split('&'))
            weibo['uid'] =  source['uid']
            weibo['uname'] = uid2uname[weibo['uid']]
            weibo['directed_uid'] = str(source['directed_uid'])
            weibo['directed_uname'] = uid2uname[str(source['directed_uid'])]
            weibo_list.append(weibo)

    return weibo_list
开发者ID:ferrero-zhang,项目名称:user_portrait_0324,代码行数:53,代码来源:utils.py

示例9: read_flow_text_sentiment

def read_flow_text_sentiment(uid_list):
    """
        读取用户微博(返回结果有微博情绪标签):
        输入数据:uid_list(字符串型列表)
        输出数据:word_dict(用户分词结果字典),weibo_list(用户微博列表)
        word_dict示例:{uid1:{'w1':f1,'w2':f2...}...}
        weibo_list示例:[[uid1,text1,s1,ts1],[uid2,text2,s2,ts2],...](每一条记录对应四个值:uid、text、sentiment、timestamp)
    """
    word_dict = dict()  # 词频字典
    weibo_list = []  # 微博列表
    now_ts = time.time()
    now_date_ts = datetime2ts(ts2datetime(now_ts))
    now_date_ts = datetime2ts("2013-09-08")
    start_date_ts = now_date_ts - DAY * WEEK
    for i in range(0, WEEK):
        iter_date_ts = start_date_ts + DAY * i
        flow_text_index_date = ts2datetime(iter_date_ts)
        flow_text_index_name = flow_text_index_name_pre + flow_text_index_date
        print flow_text_index_name
        try:
            flow_text_exist = es_flow_text.search(
                index=flow_text_index_name,
                doc_type=flow_text_index_type,
                body={"query": {"filtered": {"filter": {"terms": {"uid": uid_list}}}}, "size": MAX_VALUE},
                _source=False,
                fields=["text", "uid", "sentiment", "keywords_dict", "timestamp"],
            )["hits"]["hits"]
        except:
            flow_text_exist = []

        for flow_text_item in flow_text_exist:
            uid = flow_text_item["fields"]["uid"][0].encode("utf-8")
            text = flow_text_item["fields"]["text"][0].encode("utf-8")
            sentiment = int(flow_text_item["fields"]["sentiment"][0])
            ts = flow_text_item["fields"]["timestamp"][0]
            keywords_dict = json.loads(flow_text_item["fields"]["keywords_dict"][0])
            keywords_dict = json.dumps(keywords_dict, encoding="UTF-8", ensure_ascii=False)
            keywords_dict = eval(keywords_dict)

            if word_dict.has_key(uid):
                item_dict = Counter(word_dict[uid])
                keywords_dict = Counter(keywords_dict)
                item_dict = dict(item_dict + keywords_dict)
                word_dict[uid] = item_dict
            else:
                word_dict[uid] = keywords_dict

            weibo_list.append([uid, text, sentiment, ts])

    return word_dict, weibo_list
开发者ID:jianjian0dandan,项目名称:sensitive_user_portrait,代码行数:50,代码来源:weibo_api.py

示例10: get_influence_content

def get_influence_content(uid, timestamp_from, timestamp_to):
    weibo_list = []
    #split timestamp range to new_range_dict_list
    from_date_ts = datetime2ts(ts2datetime(timestamp_from))
    to_date_ts = datetime2ts(ts2datetime(timestamp_to))
    new_range_dict_list = []
    if from_date_ts != to_date_ts:
        iter_date_ts = from_date_ts
        while iter_date_ts < to_date_ts:
            iter_next_date_ts = iter_date_ts + DAY
            new_range_dict_list.append({'range':{'timestamp':{'gte':iter_date_ts, 'lt':iter_next_date_ts}}})
            iter_date_ts = iter_next_date_ts
        if new_range_dict_list[0]['range']['timestamp']['gte'] < timestamp_from:
            new_range_dict_list[0]['range']['timestamp']['gte'] = timestamp_from
        if new_range_dict_list[-1]['range']['timestamp']['lt'] > timestamp_to:
            new_range_dict_list[-1]['range']['timestamp']['lt'] = timestamp_to
    else:
        new_range_dict_list = [{'range':{'timestamp':{'gte':timestamp_from, 'lt':timestamp_to}}}]
    #iter date to search flow_text
    iter_result = []
    for range_item in new_range_dict_list:
        range_from_ts = range_item['range']['timestamp']['gte']
        range_from_date = ts2datetime(range_from_ts)
        flow_text_index_name = flow_text_index_name_pre + range_from_date
        query = []
        query.append({'term':{'uid':uid}})
        query.append(range_item)
        try:
            flow_text_exist = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body={'query':{'bool':{'must': query}}, 'sort':[{'timestamp':'asc'}]})['hits']['hits']
        except:
            flow_text_exist = []
        iter_result.extend(flow_text_exist)
    # get weibo list
    for item in flow_text_exist:
        source = item['_source']
        weibo = {}
        weibo['timestamp'] = ts2date(source['timestamp'])
        weibo['ip'] = source['ip']
        weibo['text'] = source['text']
        if source['geo']:
            weibo['geo'] = '\t'.join(source['geo'].split('&'))
        else:
            weibo['geo'] = ''
        weibo_list.append(weibo)
        
    return weibo_list
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:47,代码来源:utils.py

示例11: read_flow_text_sentiment

def read_flow_text_sentiment(uid_list):
    '''
        读取用户微博(返回结果有微博情绪标签):
        输入数据:uid_list(字符串型列表)
        输出数据:word_dict(用户分词结果字典),weibo_list(用户微博列表)
        word_dict示例:{uid1:{'w1':f1,'w2':f2...}...}
        weibo_list示例:[[uid1,text1,s1,ts1],[uid2,text2,s2,ts2],...](每一条记录对应四个值:uid、text、sentiment、timestamp)
    '''
    word_dict = dict()#词频字典
    weibo_list = []#微博列表
    now_ts = time.time()
    now_date_ts = datetime2ts(ts2datetime(now_ts))
    now_date_ts = datetime2ts('2013-09-08')
    start_date_ts = now_date_ts - DAY * WEEK
    for i in range(0,WEEK):
        iter_date_ts = start_date_ts + DAY * i
        flow_text_index_date = ts2datetime(iter_date_ts)
        flow_text_index_name = flow_text_index_name_pre + flow_text_index_date
        print flow_text_index_name
        try:
            flow_text_exist = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body={'query':{'filtered':{'filter':{'terms':{'uid': uid_list}}}}, 'size': MAX_VALUE}, _source=False,  fields=['text','uid','sentiment','keywords_dict','timestamp'])['hits']['hits']
        except:
            flow_text_exist = []

        for flow_text_item in flow_text_exist:
            uid = flow_text_item['fields']['uid'][0].encode('utf-8')
            text = flow_text_item['fields']['text'][0].encode('utf-8')
            sentiment = int(flow_text_item['fields']['sentiment'][0])
            ts = flow_text_item['fields']['timestamp'][0]
            keywords_dict = json.loads(flow_text_item['fields']['keywords_dict'][0])
            keywords_dict = json.dumps(keywords_dict, encoding="UTF-8", ensure_ascii=False)
            keywords_dict = eval(keywords_dict)

            if word_dict.has_key(uid):
                item_dict = Counter(word_dict[uid])
                keywords_dict = Counter(keywords_dict)
                item_dict = dict(item_dict + keywords_dict)
                word_dict[uid] = item_dict
            else:
                word_dict[uid] = keywords_dict

            weibo_list.append([uid,text,sentiment,ts])
            
    return  word_dict,weibo_list
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:45,代码来源:weibo_api.py

示例12: group_user_weibo

def group_user_weibo(task_name, submit_user, sort_type):
    weibo_list = []
    now_date = ts2datetime(time.time())
    #run_type
    if RUN_TYPE == 0:
        now_date = RUN_TEST_TIME
        sort_type = 'timestamp'
    #step1: get group user
    task_id = submit_user + '-' + task_name
    try:
        group_exist_result = es_group_result.get(index=group_index_name, doc_type=group_index_type,\
                id=task_id)['_source']
    except:
        group_exist_result = {}
    if not group_exist_result:
        return 'group no exist'
    #step2: get user weibo list
    uid_list = group_exist_result['uid_list']
    for i in range(7,0,-1):
        iter_date = ts2datetime(datetime2ts(now_date) - i * DAY)
        index_name = flow_text_index_name_pre + iter_date
        try:
            weibo_result = es_flow_text.search(index=index_name, doc_type=flow_text_index_type,\
                    body={'query':{'filtered':{'filter':{'terms':{'uid': uid_list}}}}, 'sort':sort_type, 'size':100})['hits']['hits']
        except:
            weibo_result = []
        if weibo_result:
            weibo_list.extend(weibo_result)
    sort_weibo_list = sorted(weibo_list, key=lambda x:x['_source'][sort_type], reverse=True)[:100]
    #step3: get user name
    try:
        portrait_exist_result = es_user_portrait.mget(index=portrait_index_name, doc_type=portrait_index_type, \
                body={'ids':uid_list})['docs']
    except:
        portrait_exist_result = []
    uid2uname_dict = {}
    for portrait_item in portrait_exist_result:
        uid = portrait_item['_id']
        if portrait_item['found'] == True:
            source = portrait_item['_source']
            uname = source['uname']
        else:
            uname = 'unknown'
        uid2uname_dict[uid] = uname
    weibo_list = []
    for weibo_item in sort_weibo_list:
        source = weibo_item['_source']
        mid = source['mid']
        uid = source['uid']
        uname = uid2uname_dict[uid]
        text = source['text']
        ip = source['geo']
        timestamp = source['timestamp']
        date = ts2date(timestamp)
        sentiment = source['sentiment']
        weibo_url = weiboinfo2url(uid, mid)
        #run_type:
        if RUN_TYPE == 1:
            retweet_count = source['retweet_count']
            comment_count = source['comment_count']
            sensitive_score = source['sensitive_score']
        else:
            retweet_count = 0
            comment_count = 0
            sensitive_score = 0
        city = ip2city(ip)
        weibo_list.append([mid, uid, uname, text, ip, city, timestamp, date, retweet_count, comment_count, sensitive_score, weibo_url])
    return weibo_list
开发者ID:ferrero-zhang,项目名称:user_portrait_0324,代码行数:68,代码来源:utils.py

示例13: search_retweet_network_keywords

def search_retweet_network_keywords(task_id, uid):
    results = {}
    task_results = es_network_task.get(index=network_keywords_index_name, \
                doc_type=network_keywords_index_type, id=task_id)['_source']

    start_date = task_results['start_date']
    start_ts = datetime2ts(start_date)
    end_date = task_resuts['end_date']
    end_ts = datetime2ts(end_date)
    iter_date_ts = start_ts
    to_date_ts = end_ts
    iter_query_date_list = [] # ['2013-09-01', '2013-09-02']
    while iter_date_ts <= to_date_ts:
        iter_date = ts2datetime(iter_date_ts)
        iter_query_date_list.append(iter_date)
        iter_date_ts += DAY
    #step2: get iter search flow_text_index_name
    #step2.1: get search keywords list
    query_must_list = []
    keyword_nest_body_list = []
    keywords_string = task_results['query_keywords']
    keywords_list = keywords_string.split('&')
    for keywords_item in keywords_list:
        keyword_nest_body_list.append({'wildcard': {'text': '*' + keywords_item + '*'}})
    query_must_list.append({'bool': {'should': keyword_nest_body_list}})
    network_results = {}
    retweet_query = query_must_list
    be_retweet_query = query_must_list
    #retweet
    retweet_query.append({'term': {'uid': uid}})
    item_results = {}
    for iter_date in iter_query_date_list:
        flow_text_index_name = flow_text_index_name_pre + iter_date
        query_body = {
            'query':{
                'bool':{
                    'must':retweet_query
                }
            },
            'size': 100
        }
        flow_text_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body=query_body)['hits']['hits']
        for item in flow_text_result:
            source = item['_source']
            source_uid = source['directed_uid']
            try:
                item_results[source_uid] += 1
            except:
                item_results[source_uid] = 1
    results = retweet_dict2results(uid, item_results)
    network_results['retweet'] = results
    #be_retweet
    retweet_query.append({'term': {'directed_uid': uid}})
    item_results = {}
    for iter_date in iter_query_date_list:
        flow_text_index_name = flow_text_index_name_pre + iter_date
        query_body = {
            'query':{
                'bool':{
                    'must':retweet_query
                }
            },
            'size': 100
        }
        flow_text_result = es_flow_text.search(index=flow_text_index_name, doc_type=flow_text_index_type,\
                    body=query_body)['hits']['hits']
        for item in flow_text_result:
            source = item['_source']
            source_uid = source['directed_uid']
            try:
                item_results[source_uid] += 1
            except:
                item_results[source_uid] = 1
    results = retweet_dict2results(uid, item_results)
    network_results['be_retweet'] = results
    return network_results 
开发者ID:jianjian0dandan,项目名称:user_portrait_0324,代码行数:77,代码来源:utils.py

示例14: influenced_detail

def influenced_detail(uid, date, style):
    date1 = str(date).replace('-', '')
    index_name = pre_index + date1
    index_text = "flow_text_" + date
    #detail_text = {}
    style = int(style)
    try:
        user_info = es_cluster.get(index=index_name, doc_type=influence_doctype, id=uid)["_source"]
    except:
        result = {}
        return result
    origin_retweetd_dict = json.loads(user_info["origin_weibo_retweeted_detail"])
    origin_comment_dict = json.loads(user_info['origin_weibo_comment_detail'])
    retweeted_retweeted_dict = json.loads(user_info["retweeted_weibo_retweeted_detail"])
    retweeted_comment_dict = json.loads(user_info["retweeted_weibo_comment_detail"])

    origin_retweetd = sorted(origin_retweetd_dict.items(), key=lambda x:x[1], reverse=True)
    origin_comment = sorted(origin_comment_dict.items(), key=lambda x:x[1], reverse=True)
    retweeted_retweeted = sorted(retweeted_retweeted_dict.items(), key=lambda x:x[1], reverse=True)
    retweeted_comment = sorted(retweeted_comment_dict.items(), key=lambda x:x[1], reverse=True)

    query_body_origin = {
        "query":{
            "filtered":{
                "filter":{
                    "bool":{
                        "must":[
                            {"term":{"message_type": 1}},
                            {"term":{"uid": uid}}
                        ]
                    }
                }
            }
        },
        "size": 10000
    }
    result_1 = es.search(index=index_text, doc_type="text", body=query_body_origin)['hits']['hits']
    origin_set = set()
    if result_1:
        for item in result_1:
            origin_set.add(item['_id'])

    query_body_retweeted = {
        "query":{
            "filtered":{
                "filter":{
                    "bool":{
                        "must":[
                            {"term":{"message_type": 3}},
                            {"term":{"uid": uid}}
                        ]
                    }
                }
            }
        },
        "size": 10000
    }
    result_2 = es.search(index=index_text, doc_type="text", body=query_body_retweeted)['hits']['hits']
    retweeted_set = set()
    if result_2:
        for item in retweeted_set:
            retweeted_set.add(item['_id'])
    
    if origin_retweetd:
        for item in origin_retweetd:
            if item[0] not in origin_set:
                origin_retweetd.remove(item)

    if origin_comment:
        for item in origin_comment:
            if item[0] not in origin_set:
                origin_comment.remove(item)

    if retweeted_retweeted:
        for item in retweeted_retweeted:
            if item[0] not in retweeted_set:
                retweeted_retweeted.remove(item)

    if retweeted_comment:
        for item in retweeted_comment:
            if item[0] not in retweeted_set:
                retweeted_comment.remove(item)

    if style == 0:
        detail_text = get_text(origin_retweetd[:20], date, user_info, style)
    elif style == 1:
        detail_text = get_text(origin_comment[:20], date, user_info, style)
    elif style == 2:
        detail_text = get_text(retweeted_retweeted[:20], date, user_info, style)
    else:
        detail_text = get_text(retweeted_comment[:20], date, user_info, style)
    #detail_text["origin_retweeted"] = get_text(origin_retweetd, date)
    #detail_text["origin_comment"] = get_text(origin_comment, date)
    #detail_text["retweeted_retweeted"] = get_text(retweeted_retweeted, date)
    #detail_text["retweeted_comment"] = get_text(retweeted_comment, date)

    return detail_text
开发者ID:ferrero-zhang,项目名称:user_portrait_0324,代码行数:97,代码来源:personal_influence.py

示例15: aggregation_hot_keywords

def aggregation_hot_keywords(start_time, stop_time, keywords_list):
    start_time = int(start_time)
    stop_time = int(stop_time)
    query_body = {
        "query":{
            "filtered":{
                "filter":{
                    "bool":{
                        "must":[
                            {"terms": {"keywords_string": keywords_list}},
                            {"range":{
                                "timestamp":{
                                    "gte":start_time,
                                    "lt": stop_time
                                }
                            }}
                        ]
                    }
                }
            }
        },
        "aggs":{
            "all_keywords":{
                "terms": {"field": "keywords_string", "size": PRE_AGGREGATION_NUMBER}
            }
        }
    }


    keywords_dict = dict()
    datetime = ts2datetime(float(stop_time))
    index_name = flow_text_index_name_pre + datetime
    exist_es = es_text.indices.exists(index_name)
    if exist_es:
        search_results = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["aggregations"]['all_keywords']['buckets']
        if search_results:
            for item in search_results:
                keywords_dict[item['key']] = item['doc_count']

    datetime_1 = ts2datetime(float(start_time))
    if datetime_1 == datetime:
        pass
    else:
        ts = float(stop_time)
        while 1:
            keywords_dict_1 = dict()
            ts = ts-day_time
            datetime = ts2datetime(ts)
            index_name = flow_text_index_name_pre + datetime
            exist_es = es_text.indices.exists(index_name)
            if exist_es:
                search_results_1 = es_text.search(index=index_name, doc_type=flow_text_index_type, body=query_body)["aggregations"]['all_keywords']['buckets']
                if search_results_1:
                    print search_results_1
                    for item in search_results_1:
                        keywords_dict_1[item['key']] = item['doc_count']
                for iter_key in keywords_dict_1.keys():
                    if keywords_dict.has_key(iter_key):
                        keywords_dict[iter_key] += keywords_dict_1[iter_key]
                    else:
                        keywords_dict[iter_key] = keywords_dict_1[iter_key]
            if datetime_1 == datetime:
                break
    print keywords_dict
    return_dict = sorted(keywords_dict.items(), key=lambda x:x[1], reverse=True)[:AGGRAGATION_KEYWORDS_NUMBER]
    return return_dict
开发者ID:huxiaoqian,项目名称:user_portrait,代码行数:66,代码来源:full_text_serach.py


注:本文中的user_portrait.global_utils.es_flow_text.search函数示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。