Python3，从csv文件中计算单词频率的字典

Question

我正在尝试编写一个函数来读取具有不同学位的学生志愿者的 CSV 文件。该函数的目的是创建一个字典，其中键是度数，值是度数的频率。

数据组织如下；

name    degree     email

ABC     PhD.       abd@gmail.com
CDE     Ph.D.      cde@gmail.com
FGH     MD,PHD     fgh@gmail.com

旨在获取字典如下：

#degree_count{'phd':3,'md':1}

def degree_frequency(csv_file):
    f = open('csv_file')
    csv_f = csv.reader(f)
    #Creating a list to store all the degrees from the csv file
    student_degree_list=[]
    #Creating an empty dictionary to count the frequency
    degree_count={}
    for row in csv_f:
        student_degree_list.append(row[1]) 
    #Replacing fullstops to account for variations in writing degrees ( eg JD vs J.D)
    [word.replace(".", "") for word in student_degree_list]
    [word.lower() for word in student_degree_list]
    for ele in student_degree_list:
        if ele in degree_count:
            degree_count[ele]=degree_count[ele]+1
        else:
            degree_count[ele]=0
    return degree_count

Answer 1

我相信您的问题是，除非您将其分配给变量，否则以下代码无效。

[word.replace(".", "") for word in student_degree_list]
[word.lower() for word in student_degree_list]

另外，如果一个度数出现 1 次，它不应该设置为 1 而不是 0 吗？

工作代码：

#degree_count{'phd':3,'md':1}

def degree_frequency():
    f = open('csv_file')
    csv_f = csv.reader(f)
    # Creating a list to store all the degrees from the csv file
    student_degree_list = []
    # Creating an empty dictionary to count the frequency
    degree_count = {}
    for row in csv_f:
        student_degree_list.append(row[1])
    #Replacing fullstops to account for variations in writing degrees ( eg JD vs J.D)
    student_degree_list = [word.replace('.','').lower() for word in student_degree_list]
    for ele in student_degree_list:
        if ele in degree_count:
            degree_count[ele] += 1
        else:
            # Supposed to be 1?
            degree_count[ele]=0
    return degree_count

Answer 2

import csv 
from collections import Counter

columns = defaultdict(list) # each value in each column is appended to a list

with open('csv_file.csv') as f:
    reader = csv.DictReader(f) # read rows into a dictionary format
    for row in reader: # read a row as {column1: value1, column2: value2,...}
        for (k,v) in row.items(): # go over each column name and value 
            columns[k].append(v) # append the value into the appropriate list
                                 # based on column name k

感谢csv reader code

degree_list = columns['degree']
degree_list_clean = []

for cad_degrees in degree_list:
    cad_degrees_lst = cad_degrees.split()
    for degree in cad_degrees_lst:
        degree_clean = degree.strip().replace('.','').lower()
        degree_list_clean.append(degree_clean)

选项 1

output_dict_counter_version = dict(Counter(degree_list_clean))
print(output_dict_counter_version)

选项 2

degree_frequency_dict = {}

for deg in degree_list_clean:
    if deg in degree_frequency_dict:
        degree_frequency_dict[deg] += 1
    else:
        degree_frequency_dict[deg] = 1

print(degree_frequency_dict)    

使用熊猫

import pandas as pd
from collections import Counter

data = pd.read_csv("csv_file.csv")
degree_list = data['degree'].tolist()


degree_list_clean = []

for cad_degrees in degree_list:
    cad_degrees_lst = cad_degrees.split()
    for degree in cad_degrees_lst:
        degree_clean = degree.strip().replace('.','').lower()
        degree_list_clean.append(degree_clean)

print(dict(Counter(degree_list_clean)))



'''
------------------ Input
name,degree,email
ABC,PhD. ,abd@gmail.com
CDE,Ph.D. ,cde@gmail.com
FGH, MD PHD ,fgh@gmail.com

-------------------- Output
{'phd': 3, 'md': 1}
'''