Question

是的，我又来了。这是一个与我在Twitter数据上称为情感分析的项目相关的代码。以下代码主要用于显示正负推文的数量，我在下面给出了错误。

from pyspark import SparkConf, SparkContext
from pyspark.streaming import StreamingContext
from pyspark.streaming.kafka import KafkaUtils
import operator
import numpy as np
import matplotlib.pyplot as plt


def main():
        conf = SparkConf().setMaster("local[2]").setAppName("Streamer")
        sc = SparkContext(conf=conf)

        # Creating a streaming context with batch interval of 10 sec
        ssc = StreamingContext(sc, 10)
        ssc.checkpoint("checkpoint")
        pwords = load_wordlist("positive.txt")
        nwords = load_wordlist("negative.txt")
        counts = stream(ssc, pwords, nwords, 100)
        make_plot(counts)


def make_plot(counts):
        """
        This function plots the counts of positive and negative words for each timestep.
        """
        positiveCounts = []
        negativeCounts = []
        time = []

        for val in counts:
        positiveTuple = val[0]
        positiveCounts.append(positiveTuple[1])
        negativeTuple = val[1]
        negativeCounts.append(negativeTuple[1])

        for i in range(len(counts)):
        time.append(i)

        posLine = plt.plot(time, positiveCounts,'bo-', label='Positive')
        negLine = plt.plot(time, negativeCounts,'go-', label='Negative')
        plt.axis([0, len(counts), 0, max(max(positiveCounts), max(negativeCounts))+50])
        plt.xlabel('Time step')
        plt.ylabel('Word count')
        plt.legend(loc = 'upper left')
    plt.show()


def load_wordlist(filename):
    """ 
    This function returns a list or set of words from the given filename.
    """ 
    words = {}
    f = open(filename, 'rU')
    text = f.read()
    text = text.split('\n')
    for line in text:
        words[line] = 1
    f.close()
    return words


def wordSentiment(word,pwords,nwords):
    if word in pwords:
    return ('positive', 1)
    elif word in nwords:
    return ('negative', 1)


def updateFunction(newValues, runningCount):
    if runningCount is None:
       runningCount = 0
    return sum(newValues, runningCount) 


def sendRecord(record):
    connection = createNewConnection()
    connection.send(record)
    connection.close()


def stream(ssc, pwords, nwords, duration):
    kstream = KafkaUtils.createDirectStream(
    ssc, topics = ['twitterstream'], kafkaParams = {"metadata.broker.list": 'localhost:9092'})
    tweets = kstream.map(lambda x: x[1].encode("ascii", "ignore"))

    # Each element of tweets will be the text of a tweet.
    # We keep track of a running total counts and print it at every time step.
    words = tweets.flatMap(lambda line:line.split(" "))
    positive = words.map(lambda word: ('Positive', 1) if word in pwords else ('Positive', 0))
    negative = words.map(lambda word: ('Negative', 1) if word in nwords else ('Negative', 0))
    allSentiments = positive.union(negative)
    sentimentCounts = allSentiments.reduceByKey(lambda x,y: x+y)
    runningSentimentCounts = sentimentCounts.updateStateByKey(updateFunction)
    runningSentimentCounts.pprint()

    # The counts variable hold the word counts for all time steps
    counts = []
    sentimentCounts.foreachRDD(lambda t, rdd: counts.append(rdd.collect()))

    # Start the computation
    ssc.start() 
    ssc.awaitTerminationOrTimeout(duration)
    ssc.stop(stopGraceFully = True)

    return counts


if __name__=="__main__":
    main()

错误恰好如下：

Traceback (most recent call last):
  File "/usr/local/lib/python2.7/dist-packages/matplotlib/backends/backend_gtk3.py", line 343, in idle_draw
    self.draw()
  File "/usr/local/lib/python2.7/dist-packages/matplotlib/backends/backend_gtk3.py", line 336, in draw
    self.get_property("window").process_updates (False)
TypeError: Couldn't find foreign struct converter for 'cairo.Context'

Answer 1

见Github discussion。例如，尝试：

MATCH path = (a)-[r]-(b)
RETURN count(path) AS nPaths, count(distinct r) AS nRels;

Answer 2

这里的问题是matplotlib的后端GTK3。我建议将其更改为适合您的后端。见https://matplotlib.org/faq/usage_faq.html

我经常做

import matplotlib
matplotlib.use('Agg')

在与matplotlib相关的任何导入之前。您将无法看到该图，但可以使用savefig（）保存它，然后使用图像查看器打开它。

Answer 3

在3年前回复以上评论（我正在使用WSL 2和VSCode，以及用于GUI应用程序的X服务器），

sudo apt install python3-gi-cairo

您将省去更改后端的麻烦。

Answer 4

就我而言，python3-gi-cairo 已安装但可能已损坏。因此，如果有人遇到这种情况，您只需在 apt 安装中添加 --reinstall。

sudo apt install --reinstall python3-gi-cairo

在此处重新安装不会破坏您的系统，因为当您删除（所有依赖项也将被删除）然后再次安装时。

无法找到cairo.Context＆＃39;的外来结构转换器。

4 个答案: