统计中国，美国，世界排名前50的关键词并进行比较

1 获取中国所有关键词

import pymysql
import json

conn= pymysql.connect(
        host=‘localhost‘,
        port = 3306,
        user=‘root‘,
        passwd=‘‘,
        db =‘python‘,
        )
cursor = conn.cursor()

sql = "SELECT union_kwd_str,pmc_id FROM alzheimer where authorinfor like ‘%china%‘ && union_kwd_str != ‘‘"
a = cursor.execute(sql)
print a
b = cursor.fetchmany(a)  #b has 7887 abstract list

abstract_list = []
pmc_id_dict= {}

for j in range(a):
    abstract_list.append(b[j][0])
    pmc_id_dict[j] = b[j][1]

def output_to_json(data,filename):
    with open(filename,‘w‘) as file:
        file.write(json.dumps(data))
        file.close()
    return json.dumps(data)

output_data = {
        ‘country‘: "china",
        ‘count‘: a,
        ‘keyword‘: abstract_list
    }
output_to_json(output_data, ‘1203_china_kwd.json‘)

选出排名前50的关键词

import re
import collections
import json

def input_from_json(filename):
    with open(filename,‘r‘) as file:
        data = json.loads(file.read())
        file.close()
        return data

def count_word(path):
    result = {}
    keyword_list = input_from_json(path)[‘keyword‘]
    for all_the_text in keyword_list:
        for word in all_the_text.split(‘,‘):
            if word not in result:
                result[word] = 0
            result[word] += 1
    return result

def sort_by_count(d):  

    d = collections.OrderedDict(sorted(d.items(), key = lambda t: -t[1]))
    return d  

if __name__ == ‘__main__‘:
    file_name = "1203_china_kwd.json"
    fobj1 = open(‘1204_top50_china_kwd_list.json‘,‘w‘)
    fobj2 = open(‘1203_top15_china_kwd.json‘,‘w‘)

    dword = count_word(file_name)
    dword = sort_by_count(dword)  

    jsonlist = []
    num = 0

    top_china_kwd_list = []
    for key,value in dword.items():
        num += 1
        key = re.sub("_", " ", key)
        data = {
        ‘name‘: key,
        ‘value‘: value
        }
        json_data = json.dumps(data)

        if num < 50:
            top_china_kwd_list.append(key)
            fobj2.write(json_data)
            fobj2.write(‘,‘)
        if num == 50:
            top_china_kwd_list.append(key)
            fobj2.write(json_data)

    data = {
    ‘china_kwd‘:top_china_kwd_list
    }
    json_data = json.dumps(data)
    fobj1.write(json_data)

2.获取美国的所有关键词，并做统计，与中国的统计代码相似，下一步工作是整合代码。

import pymysql
import json

conn= pymysql.connect(
        host=‘localhost‘,
        port = 3306,
        user=‘root‘,
        passwd=‘‘,
        db =‘python‘,
        )
cursor = conn.cursor()

sql = "SELECT union_kwd_str,pmc_id FROM alzheimer where authorinfor like ‘%USA%‘ && union_kwd_str != ‘‘"
a = cursor.execute(sql)
print a
b = cursor.fetchmany(a)  #b has 7887 abstract list

abstract_list = []
pmc_id_dict= {}

for j in range(a):
    abstract_list.append(b[j][0])
    pmc_id_dict[j] = b[j][1]

def output_to_json(data,filename):
    with open(filename,‘w‘) as file:
        file.write(json.dumps(data))
        file.close()
    return json.dumps(data)

output_data = {
        ‘country‘: "USA",
        ‘count‘: a,
        ‘keyword‘: abstract_list
    }
output_to_json(output_data, ‘1204_USA_kwd.json‘)

美国前50的关键词

import re
import collections
import json

def input_from_json(filename):
    with open(filename,‘r‘) as file:
        data = json.loads(file.read())
        file.close()
        return data

def count_word(path):
    result = {}
    keyword_list = input_from_json(path)[‘keyword‘]
    for all_the_text in keyword_list:
        for word in all_the_text.split(‘,‘):
            if word not in result:
                result[word] = 0
            result[word] += 1
    return result

def sort_by_count(d):  

    d = collections.OrderedDict(sorted(d.items(), key = lambda t: -t[1]))
    return d  

if __name__ == ‘__main__‘:
    file_name = "1204_USA_kwd.json"
    fobj1 = open(‘1204_top50_USA_kwd_list.json‘,‘w‘)
    fobj2 = open(‘1204_top50_USA_kwd.json‘,‘w‘)

    dword = count_word(file_name)
    dword = sort_by_count(dword)  

    jsonlist = []
    num = 0

    top_USA_kwd_list = []
    for key,value in dword.items():
        num += 1
        key = re.sub("_", " ", key)
        data = {
        ‘name‘: key,
        ‘value‘: value
        }
        json_data = json.dumps(data)

        if num < 50:
            top_USA_kwd_list.append(key)
            fobj2.write(json_data)
            fobj2.write(‘,‘)
        if num == 50:
            top_USA_kwd_list.append(key)
            fobj2.write(json_data)

    data = {
    ‘USA_kwd‘:top_USA_kwd_list
    }
    json_data = json.dumps(data)
    fobj1.write(json_data)

3，世界的前50的关键词

import pymysql
import json

conn= pymysql.connect(
        host=‘localhost‘,
        port = 3306,
        user=‘root‘,
        passwd=‘‘,
        db =‘python‘,
        )
cursor = conn.cursor()

sql = "SELECT union_kwd_str,pmc_id FROM alzheimer where  union_kwd_str != ‘‘"
a = cursor.execute(sql)
print a
b = cursor.fetchmany(a)  #b has 7887 abstract list

abstract_list = []
pmc_id_dict= {}

for j in range(a):
    abstract_list.append(b[j][0])
    pmc_id_dict[j] = b[j][1]

def output_to_json(data,filename):
    with open(filename,‘w‘) as file:
        file.write(json.dumps(data))
        file.close()
    return json.dumps(data)

output_data = {
        ‘country‘: "world",
        ‘count‘: a,
        ‘keyword‘: abstract_list
    }
output_to_json(output_data, ‘1203_world_kwd.json‘)

世界前50关键词

import re
import collections
import json

def input_from_json(filename):
    with open(filename,‘r‘) as file:
        data = json.loads(file.read())
        file.close()
        return data

def count_word(path):
    result = {}
    keyword_list = input_from_json(path)[‘keyword‘]
    for all_the_text in keyword_list:
        for word in all_the_text.split(‘,‘):
            if word not in result:
                result[word] = 0
            result[word] += 1
    return result

def sort_by_count(d):  

    d = collections.OrderedDict(sorted(d.items(), key = lambda t: -t[1]))
    return d  

if __name__ == ‘__main__‘:
    file_name = "1203_world_kwd.json"
    fobj1 = open(‘1204_top50_world_kwd_list.json‘,‘w‘)
    fobj2 = open(‘1203_top15_world_kwd.json‘,‘w‘)

    dword = count_word(file_name)
    dword = sort_by_count(dword)  

    jsonlist = []
    num = 0

    top_world_kwd_list = []
    for key,value in dword.items():
        num += 1
        key = re.sub("_", " ", key)
        data = {
        ‘name‘: key,
        ‘value‘: value
        }
        json_data = json.dumps(data)

        if num < 50:
            top_world_kwd_list.append(key)
            fobj2.write(json_data)
            fobj2.write(‘,‘)
        if num == 50:
            top_world_kwd_list.append(key)
            fobj2.write(json_data)

    data = {
    ‘world_kwd‘:top_world_kwd_list
    }
    json_data = json.dumps(data)
    fobj1.write(json_data)

4.比较中国与美国的关键词有哪些相似的，以及中国与世界的研究热点有哪些相似的

import json

def input_from_json(filename):
    with open(filename,‘r‘) as file:
        data = json.loads(file.read())
        file.close()
        return data

china_path = ‘1204_top50_china_kwd_list.json‘
world_path =  ‘1204_top50_world_kwd_list.json‘
USA_path =  ‘1204_top50_USA_kwd_list.json‘
china_kwd_list = input_from_json(china_path)[‘china_kwd‘]
world_kwd_list = input_from_json(world_path)[‘world_kwd‘]
USA_kwd_list = input_from_json(USA_path)[‘USA_kwd‘]

a = set(china_kwd_list)
b = set(world_kwd_list)
c = set(USA_kwd_list)

china_world_same_kwd =list(a&b)
for kwd in china_world_same_kwd:
    kwd = kwd.encode(‘utf-8‘)
    print kwd

print len(china_world_same_kwd)

print ‘\n‘

china_USA_same_kwd =list(a&c)
for kwd in china_USA_same_kwd:
    kwd = kwd.encode(‘utf-8‘)
    print kwd

print len(china_world_same_kwd)