首页 / 问题 / 正文

运行打包代码时出现KeyError: 0L

3 投票
1 回答
7295 浏览
提问于 2025-04-18 00:39

我有一个叫做 rra.py 的脚本，它的基本结构如下：

usn=""
usnl=[]
from bs4 import BeautifulSoup 
import re
import asys
import glob
import os
import sys
import sys 

def inputIndex():
    #some processsing

def getval():
    #some processing

def parsehtml():
    #some processsing   

def ret():
    #some processing

def main():
    inputIndex()
    ret()
    parsehtml()
    getval()
    print "watsuup"
    asys.Compavg()
    asys.compSub()
    print "nearly done"
    return 0


if __name__ == '__main__':
    inputIndex()
    main()
    asys.Compavg()
        asys.compSub()

还有另一个脚本 asys.py，我在上面的脚本 rra.py 中引入了它，内容如下：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import statsmodels.api as sm
from numpy.random import randn
import matplotlib as mpl
import seaborn as sns

sns.set_color_palette("deep", desat=.6)
mpl.rc("figure", figsize=(8, 4))

def Compavg():
    data=Total()
    markMax=[]
    markAvg=[]
    N = 5
    ind = np.arange(N)    
    width = 0.35 
    fig = plt.figure()
    ax = fig.add_subplot(111)      
    markMax.extend((data["Total"].max(),data["Total.1"].max(),data["Total.2"].max(),data["Total.3"].max(),data["Total.4"].max()))
    markAvg.extend((data["Total"].mean(),data["Total.1"].mean(),data["Total.2"].mean(),data["Total.3"].mean(),data["Total.4"].mean()))
    rects1 = ax.bar(ind, markMax, width, color='black')
    rects2 = ax.bar(ind+width, markAvg, width, color='green')
    ax.set_xlim(-width,len(ind)+width)
    ax.set_ylim(0,120)
    ax.set_ylabel('Marks')
    ax.set_title('Max, Mean and Your Marks')
    xTickMarks = ['Subject'+str(i) for i in range(1,6)]
    ax.set_xticks(ind+width)
    xtickNames = ax.set_xticklabels(xTickMarks)
    plt.setp(xtickNames, rotation=10, fontsize=10)
    ax.legend( (rects1[0], rects2[0]), ('Max', 'Mean') )
    plt.show()
    print "finished reading 1"

def compSub():
    #max_data = np.r_[data["Total"]].max()
    #bins = np.linspace(0, max_data, max_data + 1)
    data=Total()
        print data['Total']
    plt.hist(data['Total'],linewidth=0, alpha=.7)
    plt.hist(data['Total.1'],linewidth=0,alpha=.7)
    plt.hist(data['Total.2'],linewidth=0,alpha=.7)
    plt.hist(data['Total.3'],linewidth=0,alpha=.7)
    plt.hist(data['Total.4'],linewidth=0,alpha=.7)
    plt.title("Total marks Histogram")
    plt.xlabel("Value")
    plt.ylabel("Frequency")
    plt.show()
    print "finished reading 2"

def Total():
    print "going to read"
    data=pd.read_csv("output11cs.csv")
    df3=data[['Total','Total.1','Total.2','Total.3','Total.4','Total.5','Total.6','Total.7']]
    data["Main Total"]=df3.sum(axis=1)
    data = data.dropna()
    data.reset_index(drop=True)
    return data
    #compSub()
    #Compavg()

当我在虚拟环境外（甚至在虚拟环境内）执行 rra.py，使用命令 python rra.py 时，它运行得很好，并且能够绘制图表和直方图，这些都是在 asys.py 中定义的。

然后我创建了一个 'setup.py' 文件来打包它，内容如下：

from ez_setup import use_setuptools
use_setuptools()
from setuptools import setup, find_packages
from setuptools.command.test import test as TestCommand
import vturra
import sys
class PyTest(TestCommand):
    def finalize_options(self):
        TestCommand.finalize_options(self)
        self.test_args = []
        self.test_suite = True

    def run_tests(self):
        import pytest
        errcode = pytest.main(self.test_args)
        sys.exit(errcode)

setup(name="vturra",
    version=vturra.__version__,
    license='Apache Software License',
    tests_require=['pytest'],
    install_requires=['matplotlib>=1.2.1',
                      'pandas',
                      'numpy',
                      'scipy',
                      'beautifulsoup',
                      'requests',
                      'patsy',
                      'seaborn==0.2.1',
                      'BeautifulSoup4'
                     ],
    cmdclass={'test': PyTest},
    description="Downloads results from VTU website and analyzes the result",
    long_description=open('README.md').read(),
    author="Muhammed Thaha",
    author_email='mthaha1989@gmail.com',
    download_url='https://github.com/stormvirux/vturra',
    packages=find_packages(exclude='tests'),
    package_data={'vturra': ['data/*.xml']},
    include_package_data=True,
    platforms='any',
    test_suite='vturra.test.test_vturra',
    classifiers = [
        'Programming Language :: Python',
        'Development Status :: 1 - Beta',
        'Natural Language :: English',
        'Environment :: Web Environment',
        'Intended Audience :: Developers',
        'License :: OSI Approved :: Apache Software License',
        'Operating System :: OS Independent',
        'Topic :: Internet :: WWW/HTTP :: Dynamic Content',
        ],
    extras_require={
        'testing': ['pytest'],
    },
    entry_points={
        "console_scripts": [
            "vturra=vturra.rra:main"
            #"pip%s=pip:main" % sys.version[:1],
            #"pip%s=pip:main" % sys.version[:3],
        ],
    }
)

我在 virtualenv 中使用 python setup.py install 安装了这个包，安装过程一切顺利。但现在当我执行这个包 vturra 时，出现了以下错误：

Traceback (most recent call last):
  File "asys.py", line 65, in <module>
    compSub()
  File "asys.py", line 46, in compSub
    plt.hist(data['Total'],linewidth=0, alpha=.7)
  File "/home/storm/Documents/lol/local/lib/python2.7/site-packages/matplotlib/pyplot.py", line 2827, in hist
    stacked=stacked, **kwargs)
  File "/home/storm/Documents/lol/local/lib/python2.7/site-packages/matplotlib/axes.py", line 8249, in hist
    if isinstance(x, np.ndarray) or not iterable(x[0]):
  File "/home/storm/Documents/lol/local/lib/python2.7/site-packages/pandas/core/series.py", line 491, in __getitem__
    result = self.index.get_value(self, key)
  File "/home/storm/Documents/lol/local/lib/python2.7/site-packages/pandas/core/index.py", line 1032, in get_value
    return self._engine.get_value(s, k)
  File "index.pyx", line 97, in pandas.index.IndexEngine.get_value (pandas/index.c:2661)
  File "index.pyx", line 105, in pandas.index.IndexEngine.get_value (pandas/index.c:2476)
  File "index.pyx", line 149, in pandas.index.IndexEngine.get_loc (pandas/index.c:3215)
  File "hashtable.pyx", line 382, in pandas.hashtable.Int64HashTable.get_item (pandas/hashtable.c:6450)
  File "hashtable.pyx", line 388, in pandas.hashtable.Int64HashTable.get_item (pandas/hashtable.c:6394)
KeyError: 0L

不过，如果我在 main() 中注释掉函数调用 asys.compSub()，它就可以正常工作，没有任何错误。

更新 这个函数在虚拟环境外作为独立脚本执行时完全正常，但在虚拟环境内却出现了上述错误。我觉得这可能是 virtualenv 的问题，对吗？

错误处理 脚本执行 函数调用 数据可视化 打包 依赖管理 setup.py 虚拟环境

1 个回答

7

最后解决了这个问题。问题出在最新版本的pandas和matplotlib之间。系统上的pandas版本是0.10，而虚拟环境中的版本是0.13.0。所以我把虚拟环境中的pandas降级到0.10.0。

现在一切都正常了。

其实就是matplotlib和pandas版本不兼容，特别是pandas版本大于等于0.13时，使用plt.hist和一个序列会遇到这个问题。

所以你可以选择用data['Total.1'].hist()来解决。

或者把值传进去，像这样plt.hist(data['Total.1'].values,....)。

还有一种方法就是把pandas降级到低于0.13的版本。

回答于 2025-04-18 由 Python大师
分享 举报

撰写回答