fastq_stats.py 文件源码

def get_stats(self):
        import pandas as pd
        filenames, mode = self._get_files("*.json")
        if mode == "pe":
            df1 = pd.read_json(filenames[0])
            df2 = pd.read_json(filenames[1])
            df  = pd.concat([df1, df2])
            # Should have been sorted !
            df.index = ['R1', 'R2']
        else:
            df = pd.read_json(filenames[0])
            df.index = ['R1']
        df = df[["A", "C", "G", "T", "N", "n_reads", "mean quality", "GC content",
                "average read length", "total bases"]]
        for this in "ACGTN":
            df[this] /= df["total bases"] 
            df[this] *= 100
        return df