Python Query.keys方法代码示例

# 需要导入模块: from query import Query [as 别名]
# 或者: from query.Query import keys [as 别名]
    def plot_rel_prob(self, query_length, x_func, _method, plot_ratio=True, 
            plot_total_or_avg=True, plot_rel_or_all=True, 
            performance_as_legend=True, drawline=True, numbins=60, xlimit=0, 
            ylimit=0, zoom_x=0, compact_x=False, curve_fitting=False, 
            draw_individual=False, draw_all=True, oformat='eps'):
        """
        plot the P(D=1|TF=x)

        Input:
        @query_length: only plot the queries of length, 0 for all queries.
        @x_func: how to get the x-axis of the figure. By default, this should 
            be TF values. But we are flexible with other options, e.g. tf/dl
        @_method: Which method is going to be plot. The parameters should also be 
            attached, e.g. dir,mu:2500
        @plot_ratio: When this is false, plot the y-axis as the number of relevant 
            documents; When this is true, plot the y-axis as the #rel_docs/#docs
        @plot_total_or_avg: When this is true, plot the y-axis as the collection 
            total ; When this is false, plot the collection average. 
            Only available when plot_ratio is false is only available for collection-wise
        @plot_rel_or_all: When this is true, plot the y-axis as the number of 
            relevant docs ; When this is false, plot the number of all docs. 
            Only available when plot_ratio is false is only available for collection-wise
        @performance_as_legend: whether to add performance(e.g. MAP) 
            as part of the legend
        @drawline: draw the data points as line(true) or dots(false)
        @numbins: the number of bins if we choose to plot x points as bins, 0 for no bins
        @xlimit: the limit of xaxis, any value larger than this value would not 
            be plotted. default 0, meaning plot all data.
        @ylimit: the limit of yaxis, any value larger than this value would not 
            be plotted. default 0, meaning plot all data.
        @zoom: whether zoom part of the plot
        @zoom_x: the zoom start x point, 0 for no zoom.
        @compact_x: map the x to continuous integers, e.g. 1,2,3,4,....
        @oformat: output format, eps or png
        """
        collection_name = self.collection_name
        cs = CollectionStats(self.collection_path)
        doc_details = GenDocDetails(self.collection_path)
        output_root = os.path.join('collection_figures', str(query_length))
        if not os.path.exists(os.path.join(self.all_results_root, output_root)):
            os.makedirs(os.path.join(self.all_results_root, output_root))
        if query_length == 0:
            queries = Query(self.collection_path).get_queries()
        else:
            queries = Query(self.collection_path).get_queries_of_length(query_length)
        queries = {ele['num']:ele['title'] for ele in queries}
        #print qids
        rel_docs = Judgment(self.collection_path).get_relevant_docs_of_some_queries(queries.keys(), 1, 'dict')
        #print np.mean([len(rel_docs[qid]) for qid in rel_docs])
        eval_class = Evaluation(self.collection_path)
        print _method
        p = eval_class.get_all_performance_of_some_queries(
            method=_method,
            qids=queries.keys(), 
            return_all_metrics=False, 
            metrics=['map']
        )
        collection_x_dict = {}
        collection_level_maxX = 0.0
        num_cols = min(4, len(queries))
        num_rows = int(math.ceil(len(rel_docs)*1.0/num_cols))
        fig, axs = plt.subplots(nrows=num_rows, ncols=num_cols, sharex=False, sharey=False, figsize=(2*num_cols, 2*num_rows))
        font = {'size' : 5}
        plt.rc('font', **font)
        row_idx = 0
        col_idx = 0
        #idfs = [(qid, math.log(cs.get_term_IDF1(queries[qid]))) for qid in rel_docs]
        #idfs.sort(key=itemgetter(1))
        all_expected_maps = []
        if curve_fitting:
            all_fitting_results = [{'sr': [], 'ap':[], 'ap_diff':[]} for i in range(FittingModels().size())]
            all_fitting_performances = {}
        for qid in sorted(queries):
            if num_rows > 1:
                ax = axs[row_idx][col_idx]
            else:
                if num_cols > 1:
                    ax = axs[col_idx]
                else:
                    ax = axs
            col_idx += 1
            if col_idx >= num_cols:
                row_idx += 1
                col_idx = 0
            query_term = queries[qid]
            maxTF = cs.get_term_maxTF(query_term)
            #idf = math.log(cs.get_term_IDF1(query_term))
            #legend = 'idf:%.2f'%idf
            if performance_as_legend:
                legend = '\nAP:%.4f' % (p[qid]['map'] if p[qid] else 0)
            x_dict = {}
            qid_docs_len = 0
            #for row in cs.get_qid_details(qid):
            for row in doc_details.get_qid_details(qid):
                qid_docs_len += 1
                x = x_func(cs, row)
                if x > collection_level_maxX:
                    collection_level_maxX = x
                rel = (int(row['rel_score'])>=1)
                if x not in x_dict:
#.........这里部分代码省略.........