def __init__(self, flowbackend, databackend):
AnalysisBase.__init__(self, flowbackend, databackend)
self.hostInfoDB = hostinfodb.HostInfoDB()
self.hiCollectionName = common.HOST_INFORMATION_COLLECTION
self.analysisResultDict = {
"IP" : ("NUMBER(10)", "PRIMARY"),
"LASTSEEN" : ("NUMBER(10)", None),
"LASTINFOCHECK" : ("NUMBER(10)", None)
}
self.dataBackend.prepareCollection(self.hiCollectionName, self.analysisResultDict)
def __init__(self, flowbackend, databackend):
AnalysisBase.__init__(self, flowbackend, databackend)
self.hostInfoDB = hostinfodb.HostInfoDB()
self.hiCollectionName = common.HOST_INFORMATION_COLLECTION
self.analysisResultDict = {
"IP": ("NUMBER(10)", "PRIMARY"),
"LASTSEEN": ("NUMBER(10)", None),
"LASTINFOCHECK": ("NUMBER(10)", None)
}
self.dataBackend.prepareCollection(self.hiCollectionName,
self.analysisResultDict)
def __init__(self, flowbackend, databackend): AnalysisBase.__init__(self, flowbackend, databackend)
"""Plotting notebook for publication frequency per month."""
from analysis_base import AnalysisBase
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data = AnalysisBase()
bbc = data.bbc
cnn = data.cnn
nyt = data.nyt
reuters = data.reuters
bbc_per_month = bbc.groupby([pd.Grouper(key='published',
freq='M')])['content'].count()
bbc_per_month = bbc_per_month.reindex(data.raw_index_months)
bbc_per_month[np.isnan(bbc_per_month)] = 0
cnn_per_month = cnn.groupby([pd.Grouper(key='published',
freq='M')])['content'].count()
cnn_per_month = cnn_per_month.reindex(data.raw_index_months)
cnn_per_month[np.isnan(cnn_per_month)] = 0
nyt_per_month = nyt.groupby([pd.Grouper(key='published',
freq='M')])['content'].count()
nyt_per_month = nyt_per_month.reindex(data.raw_index_months)
nyt_per_month[np.isnan(nyt_per_month)] = 0
reuters_per_month = reuters.groupby([pd.Grouper(key='published',
freq='M')])['content'].count()
reuters_per_month = reuters_per_month.reindex(data.raw_index_months)
