Python - 查找提取列表中的相同值並計算連續值之間的差異

Question

我正在學習python on dataquest並嘗試解決此問題。

編寫一個函數，可以跨年提取相同的值，並計算連續值之間的差異，以顯示出生人數是增加還是減少。 例如，在1994年到2003年間，每週的出生人數是如何變化的？

我想在Jupyter解決這個問題。我是python的新手，我不確定如何開始解決這個問題。

輸入的數據在這裏以CSV格式：US births

# coding: utf-8 

# In[1]: 

text_file = open("US_births_1994-2003_CDC_NCHS.csv", "r").read() 
line_split = text_file.split("\n") 
line_split 


# In[2]: 

def read_csv(filename): 
    text = open(filename, "r").read() 
    string_list = text.split('\n')[1:] 
    final_list = [] 
    for row in string_list: 
     int_fields = [] 
     string_fields = row.split(',') 
     for item in string_fields: 
      int_fields.append(int(item)) 
     final_list.append(int_fields) 
    return(final_list) 

cdc_list = read_csv("US_births_1994-2003_CDC_NCHS.csv") 
cdc_list[0:10] 


# In[3]: 

def months_births(filename): 
    births_per_month = dict() 
    for item in filename: 
     num_month = int(item[1]) 
     num_births = int(item[4]) 
     if num_month in births_per_month: 
      births_per_month[num_month] += num_births 
     else: 
      births_per_month[num_month] = num_births 
    return(births_per_month) 

cdc_month_births = months_births(cdc_list) 
cdc_month_births 


# In[4]: 

def dow_births(filename): 
    sum_births = dict() 
    for item in filename: 
     day_week = int(item[3]) 
     day_birth = int(item[4]) 
     if day_week in sum_births: 
      sum_births[day_week] += day_birth 
     else: 
      sum_births[day_week] = day_birth 
    return(sum_births) 

cdc_day_births = dow_births(cdc_list) 
cdc_day_births 


# In[30]: 

def calc_counts(data, column): 
    sum_dict = dict() 
    for item in data: 
     col_num = item[column] 
     birth_count = int(item[4]) 
     if col_num in sum_dict: 
      sum_dict[col_num] += birth_count 
     else: 
      sum_dict[col_num] = birth_count 
    return(sum_dict) 

cdc_year_births = calc_counts(cdc_list, 0) 
cdc_month_births = calc_counts(cdc_list, 1) 
cdc_dom_births = calc_counts(cdc_list, 2) 
cdc_dow_births = calc_counts(cdc_list, 3) 


# In[31]: 

cdc_year_births 


# In[32]: 

cdc_month_births 


# In[33]: 

cdc_dom_births 


# In[34]: 

cdc_dow_births 


# In[6]: 

def min_max_dict(filename, request): 
    if request == "max": 
     max_value = max(filename, key=filename.get) 
     return(filename[max_value]) 
    else: 
     min_value = min(filename, key=filename.get) 
     return(filename[min_value]) 

max_value = min_max_dict(cdc_year_births, "max") 
print("max: ",max_value) 
min_value = min_max_dict(cdc_year_births, "min") 
print("min: ",min_value) 


# In[36]: 

def diff_in_values(filename): 
    final_dict = dict() 
    seen_set = set() 
    unique_values = list() 
    for item in filename: 
     year_count = int(item[0]) 
     birth_count = int(item[4]) 
     day_of_week = int(item[3]) 

     if birth_count not in seen_set: 
      unique_values.append(birth_count) 
      seen_set.add(birth_count) 

    return(seen_set) 

result = diff_in_values(cdc_list) 
result 

Answer 1

我也工作在同一個項目。我已經分享了你需要的部分代碼。我在GitHub上有我項目的.ipynb文件。您可能還想看看我的功能結果。乾杯!

def read_csv(birth_data_file): 
    raw_data = open(birth_data_file, "r").read() 
    raw_data = raw_data.split("\n") 
    string_list = raw_data[1:] 
    final_list = [] 
    for data in string_list: 
     int_fields = [] 
     string_fields = data.split(",") 
     for string_field in string_fields: 
      field = int(string_field) 
      int_fields.append(field) 
     final_list.append(int_fields) 
    return(final_list) 


def calc_counts(data, column): 
    births_counts = {} 
    if not column > 0 and column <= 4: 
     return("'column' must be either 1, 2, 3, or 4") 
    else: 
     for instance in data: 
      field = instance[column-1] 
      births = instance[4] 
      if field in births_counts.keys(): 
       births_counts[field] += births 
      else: 
       births_counts[field] = births 
     return(births_counts) 


# Write a function that extracts the same values across years and calculates the 
# differences between consecutive values to show if number of 
# births is increasing or decreasing. 

def check_birth_growth(birth_data_file): 
    cdc_list = read_csv(birth_data_file) 
    cdc_year_births = calc_counts(cdc_list, 1) 
    previous_year_birth = 0 
    previous_birth_diff = 0 
    for year, total_births in cdc_year_births.items(): 
     current_year_birth = int(total_births) 
     if previous_year_birth == 0: 
      growth_status = "Growth of births in {} not available.".format(year) 
      print(growth_status) 
      previous_year_birth = current_year_birth 
     else: 
      if current_year_birth > previous_year_birth: 
       growth_status = "Births increased in {}.".format(year) 
       print(growth_status) 
       previous_year_birth = current_year_birth 
      elif current_year_birth < previous_year_birth: 
       growth_status = "Births decreased in {}.".format(year) 
       print(growth_status) 
       previous_year_birth = current_year_birth 
      elif current_year_birth == previous_year_birth: 
       growth_status = "Births in {} was same as previous year.".format(year) 
       print(growth_status) 
       previous_year_birth = current_year_birth 

Answer 2

Enock奎西Addey，這似乎只會一年比較一年出生，但不能逐月或日常出生，如1994年3月比較，1995年3月