文献指标统计

import xlrd
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# 设定行名称，第1行为字段名称
#data = pd.read_excel("D:/01研/03研二/20220321help/历史 图情 经济 哲学三类文献原文及引文数据 1997-2016/历史 图情 经济 哲学三类文献原文及引文数据/Information science and Library Science/原文/ISLS.xlsx")
data = pd.read_csv("D:/01研/03研二/20220321help/历史 图情 经济 哲学三类文献原文及引文数据 1997-2016/历史 图情 经济 哲学三类文献原文及引文数据/Economics/Economic2007_2016.csv", low_memory=False)

#data.head()

# 作者数量计算
data['Author Full Names'] = data['Author Full Names'].fillna("nan")
#data['Language'] = data['Language'].fillna("0")
#data['Number of Pages'] = data['Number of Pages'].fillna("0")
#data['Cited Reference Count'] = data['Cited Reference Count'].fillna("0")

# Number of authors
data.loc[:,'Number_of_authors'] = data['Author Full Names'].apply(lambda x: len(x.split(";")))

data.info()

print("文献类型：")
df1 = data['Document_Type_new'].value_counts()
print(df1)

print("未被引文献类型：")
#df2 = data[data["Times Cited, All Databases"]==0]['Document_Type_new'].value_counts()
df2 = data[data["sum5"]==0]['Document_Type_new'].value_counts()
print(df2)

print("年度分布：")
df3 = data["Publication Year"].value_counts(sort = False)
print(df3)

print("未被引文献年度分布：")
#df4 = data[data["Times Cited, All Databases"]==0]["Publication Year"].value_counts()
df4 = data[data["sum5"]==0]["Publication Year"].value_counts(sort = False)
print(df4)

#-------------------------------------------#
# 零被引文献，完全匹配
# 零被引三类文献
#data0 = data[data["Times Cited, All Databases"]==0]
data0 = data[data["sum5"]==0]
#data0
data0_sanlei = (data0[data0["Document_Type_new"]=="Article"].append(data0[data0["Document_Type_new"]=="Proceedings Paper"])).append(data0[data0["Document_Type_new"]=="Review"])

# 三类文献
data_sanlei = (data[data["Document_Type_new"]=="Article"].append(data[data["Document_Type_new"]=="Proceedings Paper"])).append(data[data["Document_Type_new"]=="Review"])
#-------------------------------------------#
# 三类文献时间分布
print("三类文献年度分布：")
df5 = data_sanlei["Publication Year"].value_counts(sort = False)
print(df5)

# 三类文献中零被引年度分布
print("三类文献零被引年度分布：")
#df6 = data_sanlei[data["Times Cited, All Databases"]==0]["Publication Year"].value_counts()
df6 = data_sanlei[data["sum5"]==0]["Publication Year"].value_counts(sort = False)
print(df6)

# 三类文献中语言分布
print("三类文献中语言分布：")
df7 = data_sanlei["Language"].value_counts()
print(df7)

# 三类文献中零被引语言分布
print("三类文献中零被引语言分布")
#df8 = data_sanlei[data["Times Cited, All Databases"]==0]["Language"].value_counts()
df8 = data_sanlei[data["sum5"]==0]["Language"].value_counts()
print(df8)

#-------------------------------------------#
# 三类文献长度分布
data_sanlei_pages = data_sanlei["Number of Pages"]
print("三类文献页数")
p = len(data_sanlei_pages)
print(p)
a = pd.cut(data_sanlei_pages,[0,5,10,15,20,25,30,35,40,10000], labels=[u"(0,5]",u"(5,10]",u"(10,15]",u"(15,20]",u"(20,25]",u"(25,30]",u"(30,35]",u"(35,40]",u"(40,10000]"])
print("频数分布：")
b = a.value_counts().sort_index()
print(b)


data0_sanlei_pages = data0_sanlei["Number of Pages"]
a1 = pd.cut(data0_sanlei_pages,[0,5,10,15,20,25,30,35,40,10000], labels=[u"(0,5]",u"(5,10]",u"(10,15]",u"(15,20]",u"(20,25]",u"(25,30]",u"(30,35]",u"(35,40]",u"(40,10000]"])
print("三类文献中零被引文献页数")
b1 = a1.value_counts().sort_index()
print(b1)


#-------------------------------------------#
# 三类文献文献作者数量
print("三类文献作者")
data_sanlei_authors = data_sanlei["Number_of_authors"]
a2 = pd.cut(data_sanlei_authors,[0,1,2,3,4,5,6,7,10000], labels=[u"(0,1]",u"(1,2]",u"(2,3]",u"(3,4]",u"(4,5]",u"(5,6]",u"(6,7]",u"(7,10000]"])
b2 = a2.value_counts().sort_index()
print(b2)

# 三类零被引文献作者数量
print("三类文献中零被引文献作者")
data0_sanlei_authors = data0_sanlei["Number_of_authors"]
a3 = pd.cut(data0_sanlei_authors,[0,1,2,3,4,5,6,7,10000], labels=[u"(0,1]",u"(1,2]",u"(2,3]",u"(3,4]",u"(4,5]",u"(5,6]",u"(6,7]",u"(7,10000]"])
b3 = a3.value_counts().sort_index()
print(b3)


#-------------------------------------------#
# 三类文献参考文献数量
data_sanlei_references = data_sanlei["Cited Reference Count"]
data0_sanlei_references = data0_sanlei["Cited Reference Count"]
print("三类文献参考文献数量分布")
a4 = pd.cut(data_sanlei_references
           ,[0,5,10,15,20,25,30,35,40,45,50,55,60,65,70,10000]
           ,labels=[u"(0,5]",u"(5,10]",u"(10,15]",u"(15,20]",u"(20,25]",u"(25,30]",u"(30,35]",u"(35,40]",u"(40,45]",u"(45,50]",u"(50,55]",u"(55,60]",u"(60,65]",u"(65,70]",u"(70,]"])
b4 = a4.value_counts().sort_index()
print(b4)
print("total")
d = len(a4)
print(d)

# 三类零被引文献参考文献数量
print("三类文献中零被引文献参考文献")
data0_sanlei_references = data0_sanlei["Cited Reference Count"]
a5 = pd.cut(data0_sanlei_references
, [0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 10000]
, labels = [u"(0,5]", u"(5,10]", u"(10,15]", u"(15,20]", u"(20,25]", u"(25,30]", u"(30,35]", u"(35,40]", u"(40,45]",
            u"(45,50]", u"(50,55]", u"(55,60]", u"(60,65]", u"(65,70]", u"(70,]"])
b5 = a5.value_counts().sort_index()
print(b5)
l = len(a5)
print(l)