Python - 數據顯示不正確（Matplotlib）

Question

我是Python的新手，我有一個問題。我從CSV文件加載數據，刪除重複項，保存已刪除的複製csv文件，然後加載正確的CSV文件並生成圖形。然而，我的問題是，圖表沒有正確顯示，因爲總數是錯誤的。我知道該程序工作正常，因爲如果我刪除第1部分（請參閱下面的＃section1），我得到正確的數據顯示。我無法看到第1部分中的內容會導致數據偏差......任何幫助都將不勝感激。謝謝。

摘要：無法在同一個py文件中運行第1部分和第2部分，否則數據會錯誤地計入。想知道爲什麼？如何避免它而不運行單獨的py文件。

from collections import Counter 
import numpy as np 
import matplotlib 
import matplotlib.pyplot as plt 
import pandas as pd 
import csv 
import itertools 

第1

# Create database of duplicates - check if the mac and os pairs have  duplicates 
reader = csv.reader(open('Workbook1.csv', 'r'), delimiter=',') 
writer = csv.writer(open('remacos.csv', 'w'), delimiter=',') 
entries = set() 

for row in reader: 
key = (row[1], row[2]) 

if key not in entries: 
    writer.writerow(row) 
    entries.add(key) 

entries.clear() 
# Create database of duplicates - check if the mac and browser pairs  have duplicates 
reader = csv.reader(open('Workbook1.csv', 'r'), delimiter=',')  
writer = csv.writer(open('remacbrowser.csv', 'w'), delimiter=',') 
entries = set() 

for row in reader: 
key = (row[1], row[3]) 

if key not in entries: 
    writer.writerow(row) 
    entries.add(key) 

第2節

# Read Removed Duplicated entries Database and Count Values for OS. 
df = pd.read_csv('remacos.csv', index_col="mac")   
counteros = Counter(df['os']) 
os_names = counteros.keys() 
os_counts = counteros.values() 

# Read Removed Duplicated entries Database and Count Values for  Browsers. 
df = pd.read_csv('remacbrowser.csv', index_col="mac")   
counterbrowsers = Counter(df['browser']) 
browser_names = counterbrowsers.keys() 
browser_counts = counterbrowsers.values() 

創建2個條形圖和餅圖

# Plot histogram using matplotlib bar() for OS. 
indexes = np.arange(len(os_names)) 
width = 0.7 
plt.bar(indexes, os_counts, width) 
plt.xticks(indexes + width * 0.5, os_names) 
plt.show() 

# Plot histogram using matplotlib bar() for Browsers. 
indexes = np.arange(len(browser_names)) 
width = 0.7 
plt.bar(indexes, browser_counts, width) 
plt.xticks(indexes + width * 0.5, browser_names) 
plt.show() 

# Make Pie Chart for OS's 
plt.figure() 
values = os_counts 
labels = os_names 
def make_autopct(values): 
def my_autopct(pct): 
total = sum(values) 
val = int(round(pct*total/100.0)) 
return '{p:.2f}% ({v:d})'.format(p=pct,v=val) 
return my_autopct 
plt.pie(values, labels=labels, autopct=make_autopct(values)) 
#plt.pie(values, labels=labels) #autopct?? 
plt.show() 
# Make Pie Chart for Browsers 
plt.figure() 
values = browser_counts 
labels = browser_names 
def make_autopct(values): 
def my_autopct(pct): 
total = sum(values) 
val = int(round(pct*total/100.0)) 
return '{p:.2f}% ({v:d})'.format(p=pct,v=val) 
return my_autopct 
plt.pie(values, labels=labels, autopct=make_autopct(values)) 
#plt.pie(values, labels=labels) #autopct?? 
plt.show()' 

Answer 1

溶液添加「德爾writer'after每個創建重複數據庫