def _get_stats(self):
filenames, mode = self._get_files("*.json")
cols = ["A", "C", "G", "T", "N", "n_reads",
"mean quality" , "GC content", "average read length", "total bases"]
N = len(filenames)
df = pd.DataFrame(np.zeros((N, 10)), columns=cols)
indices = []
for i, filename in enumerate(filenames):
if self.tag_R1 in filename:
index = "R1"
else:
index = "R2"
if "unmapped" in filename:
index += ".unmapped"
else:
index += ".mapped"
indices.append(index)
try:
# Use a try since the subdf may be empty
subdf = pd.read_json(filename)
df.iloc[i] = subdf.iloc[0]
df.iloc[i]["A"] /= df.iloc[i]["n_reads"]
df.iloc[i]["C"] /= df.iloc[i]["n_reads"]
df.iloc[i]["G"] /= df.iloc[i]["n_reads"]
df.iloc[i]["T"] /= df.iloc[i]["n_reads"]
df.iloc[i]["N"] /= df.iloc[i]["n_reads"]
except:
pass
df.index = indices
df = df.astype({"n_reads": np.int64, "total bases": np.int64})
return df
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
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
def _get_stats(self):
filenames, mode = self._get_files("*.json")
cols = [
"A", "C", "G", "T", "N", "n_reads", "mean quality", "GC content",
"average read length", "total bases"
]
N = len(filenames)
df = pd.DataFrame(np.zeros((N, 10)), columns=cols)
indices = []
for i, filename in enumerate(filenames):
if self.tag_R1 in filename:
index = "R1"
else:
index = "R2"
if "unmapped" in filename:
index += ".unmapped"
else:
index += ".mapped"
indices.append(index)
try:
# Use a try since the subdf may be empty
subdf = pd.read_json(filename)
df.iloc[i] = subdf.iloc[0]
df.iloc[i]["A"] /= df.iloc[i]["n_reads"]
df.iloc[i]["C"] /= df.iloc[i]["n_reads"]
df.iloc[i]["G"] /= df.iloc[i]["n_reads"]
df.iloc[i]["T"] /= df.iloc[i]["n_reads"]
df.iloc[i]["N"] /= df.iloc[i]["n_reads"]
except:
pass
df.index = indices
df = df.astype({"n_reads": np.int64, "total bases": np.int64})
return df