Python学习 | 08 文件与路径

gc_content(seq)generate_kmers(seq, 3)find_motif(seq, motif)

genome.fareads.fastqvariants.vcfannotation.gtfsample.bed

文件路径   ↓open   ↓file object   ↓读取 text   ↓解析 text   ↓Python object   ↓分析   ↓写回文件

with open(”sequence.txt”, ”r”) as f:    sequence = f.read()

sequence

'ATGCGTACGT\n'

”sequence.txt”  → 文件路径”r”             → read modeopen(...)       → 打开文件f               → file objectf.read()        → 读取文件内容

sequence.txt     ↑     │     ffile object

f.read()

f = open(”sequence.txt”, ”r”)sequence = f.read()f.close()

with open(”sequence.txt”, ”r”) as f:    sequence = f.read()

with open(...) as f:    ...

with open(...) as f:    ...

r → readw → writea → append

with open(”sequence.txt”, ”r”) as f:    ...

with open(”sequence.txt”) as f:    ...

with open(”output.txt”, ”w”) as f:    ...

with open(”output.txt”, ”w”) as f:    f.write(”hello”)

with open(”log.txt”, ”a”) as f:    ...

ATGCGTGGCAATTTAACC

with open(”sequences.txt”, ”r”) as f:    text = f.read()

'ATGCGT\nGGCAAT\nTTAACC\n'

text.split(”\n”)

with open(”sequence.txt”, ”r”) as f:    for line in f:        print(line)

文件 ↓读取第 1 行 → 处理 ↓读取第 2 行 → 处理 ↓读取第 3 行 → 处理 ↓...

整个文件   ↓全部进入内存   ↓再处理

f.readline()

with open(”sequences.txt”) as f:    first_line = f.readline()

f.readlines()

[    ”ATGCGT\n”,    ”GGCAAT\n”,    ”TTAACC\n”]

read()→ 整个文件 → 一个 stringreadline()→ 一次一行 → 一个 stringreadlines()→ 所有行 → 一个 listfor line in f→ 一行一行迭代

for line in f:

f.readlines()

raw text↓parse↓structured data

ATGCGTGGCAATTTAACC

with open(”sequences.txt”) as f:    for line in f:        print(repr(line))

line = line.strip()

with open(”sequences.txt”) as f:    for line in f:        line = line.strip()        print(repr(line))

with open(”sequences.txt”) as f:    for line in f:        line = line.strip()        if line == ””:            continue        print(line)

逐行读取↓去掉换行等首尾空白↓跳过空行↓处理真正的数据

ATGCGT

with open(”sequences.tsv”) as f:    for line in f:        line = line.strip()        seq_id, seq = line.split(”\t”)        print(seq_id, seq)

seq1    ATGCGT

line.split(”\t”)

[”seq1”, ”ATGCGT”]

seq_id, seq = line.split(”\t”)

seq_id → ”seq1”seq    → ”ATGCGT”

string+split+list+unpacking+for+function+file IO

seq1    ATGCGT    6seq2    GGCAAT    6

seq_id, seq, length = line.strip().split(”\t”)

with open(”output.txt”, ”w”) as f:    f.write(”ATGCGT”)

ATGCGT

with open(”output.txt”, ”w”) as f:    f.write(”seq1”)    f.write(”seq2”)

seq1seq2

with open(”output.txt”, ”w”) as f:    f.write(”seq1\n”)    f.write(”seq2\n”)

seq1seq2

seq_id = ”seq1”seq = ”ATGCGT”length = len(seq)

with open(”output.tsv”, ”w”) as f:    f.write(f”{seq_id}\t{seq}\t{length}\n”)

seq1    ATGCGT    6

f-string+\t+\n+write

with open(”output.txt”, ”w”) as f:    print(”seq1”, file=f)    print(”seq2”, file=f)

seq1seq2

with open(”output.tsv”, ”w”) as f:    print(seq_id, seq, length, sep=”\t”, file=f)

f.write(...)

print(..., file=f)

write→ 对具体写入的字符串控制更直接print(..., file=f)→ 输出人类可读的文本非常方便

”sequence.txt”

project/├── data/│   ├── raw/│   │   └── reads.fastq│   └── genome.fa├── results/└── scripts/

filename = ”reads.fastq”path = ”data/raw” + filename

from pathlib import Path

path = Path(”data”) / ”raw” / ”reads.fastq”print(path)

from pathlib import Pathpath = Path(”data/genome.fa”)type(path)

path.name

path.stem

path.suffix

path.parent

data_dir = Path(”data”)path = data_dir / ”genome.fa”print(path)

sample = ”sample01”

path = Path(”results”) / f”{sample}.txt”path

path.exists()

path.is_file()

from pathlib import Pathpath = Path(”data/genome.fa”)if not path.exists():    raise FileNotFoundError(f”File not found: {path}”)

Path.cwd()

current working directory

Path.cwd()

/home/user/project

Path(”data/genome.fa”)

/home/user/project/data/genome.fa

data/genome.fa

current working directory

FileNotFoundError

from pathlib import Pathprint(Path.cwd())

sequences.tsv

seq1	ATGCGTseq2	GGCCAATTseq3	ATATAT

def gc_content(seq):    if len(seq) == 0:        raise ValueError(”Sequence is empty”)        gc = seq.count(”G”) + seq.count(”C”)

from pathlib import Pathdef analyze_sequences(input_path, output_path):    input_path = Path(input_path)    output_path = Path(output_path)    with open(input_path, ”r”) as infile, open(output_path, ”w”) as outfile:        outfile.write(”seq_id\tlength\tgc_content\n”)        for line in infile:            line = line.strip()            if line == ””:                continue            seq_id, seq = line.split(”\t”)            length = len(seq)            gc = gc_content(seq)            outfile.write(                f”{seq_id}\t{length}\t{gc}\n”            )

analyze_sequences(    ”sequences.tsv”,    ”sequence_summary.tsv”)

seq_id    length    gc_contentseq1      6         0.5seq2      8         0.5seq3      6         0.0

input file    ↓read    ↓parse    ↓function    ↓analysis    ↓output file

line.strip()line.split(”\t”)

seq_id, seq = ...

if line == ””:    continue

for line in infile:

gc_content(seq)

raise ValueError(...)

f”{seq_id}\t{length}\t{gc}\n”

with open(...)

Path(...)

seq1	ATGCGTseq2	GGCCAATTbad_lineseq3	ATATAT

seq_id, seq = line.split(”\t”)

def read_sequences(path):    sequences = {}    with open(path) as f:        for line_number, line in enumerate(f, start=1):            line = line.strip()            if line == ””:                continue            fields = line.split(”\t”)            if len(fields) != 2:                raise ValueError(                    f”Invalid format at line {line_number}”                )            seq_id, seq = fields            sequences[seq_id] = seq    return sequences

for line_number, line in enumerate(f, start=1):

ValueError: Invalid format at line 37

ValueError: not enough values to unpack

read.delim()read.table()readr::read_tsv()

pandas.read_csv()

FASTAFASTQVCFGFFSAM

文件→ line→ field→ parsing

text = f.read()lines = f.readlines()

with open(path) as f:    for line in f:        ...

def read_fasta(path):    ...    yield ...

file iteration+parser+generator

for seq_id, seq in read_fasta(”genome.fa”):    ...

pathopenfile objectlinestripsplitwrite

with open(”seq.txt”) as f:    x = f.read()print(repr(x))

[    ”ATGCGT”,    ”GGCAAT”,    ”TTAACC”]

def read_reads(infile):    sequences = []    with open(infile, ”r”) as f:        for line in f:            read = line.strip()            if read == ””:                continue            if ”N” in read:                continue            sequences.append(read)    return sequencesread_reads(”reads.txt”)

reads = []with open(”reads.txt”) as f:    for line in f:        read = line.strip()        if read == ””:            continue        if ”N” in read:            continue        reads.append(read)

reads = []with open(”reads.txt”) as f:    for line in f:        read = line.strip()        if read != ”” and ”N” not in read:            reads.append(read)

sample = ”sample01”from pathlib import Pathfile = (    Path(”project”) / ”data” / sample / ”reads.fastq”)print(file.name)print(file.suffix)print(file.parent)

seq1	ATGCGTseq2	GGGAAAseq3	ATATGC

{    ”seq1”: ”ATGCGT”,    ”seq2”: ”GGGAAA”,    ”seq3”: ”ATATGC”}

def read_sequences(path):    sequences  = {}    with open(path, ”r”) as f:        for line in f:            line = line.strip()            if line == ””:                continue            seq_id, seq  = line.split(”\t”)            sequences[seq_id] = seq    return sequencesread_sequences(”sequences.tsv”)

def read_sequences(path):    sequences  = {}    valid_bases = set(”ATCGN”)    with open(path, ”r”) as f:        for line_number, line in enumerate(f, start=1):            line = line.strip()            if line == ””:                continue            fields = line.split(”\t”)            if len(fields) != 2:                raise ValueError(f”Invalid format at {line_number}”)            seq_id, seq = fields            if not set(seq) <= valid_bases:                raise ValueError(f”Invalid sequence at {line_number}”)            sequences[seq_id] = seq    return sequencesread_sequences(”sequences.tsv”)

seq1	ATGCGTseq2	GGGAAAseq3	ATATGCseq4	CCCGGG

seq_id	length	gc_contentseq1	6	0.5seq2	6	0.5seq3	6	0.3333333333333333seq4	6	1.0

from pathlib import Pathdef gc_content(seq):    if len(seq) == 0:        raise ValueError(”Sequence is empty”)    gc = seq.count(”G”) + seq.count(”C”)    return gc / len(seq)def summarize_sequences(input_path, output_path):    input_path = Path(input_path)    output_path = Path(output_path)    if not input_path.exists():        raise FileNotFoundError(f”Input file not found: {input_path}”)    with open(input_path,”r”) as infile, open(output_path,”w”) as outfile:        outfile.write(”seq_id\tlength\tgc_content\n”)        for line_number, line in enumerate(infile, start=1):            line = line.strip()            if line == ””:                continue            fields = line.split(”\t”)            if len(fields) != 2:                raise ValueError(f”Invalid format at {line_number}”)            seq_id, seq = fields            length = len(seq)            gc = gc_content(seq)            outfile.write(f”{seq_id}\t{length}\t{gc}\n”)summarize_sequences(”sequences.tsv”, ”summary.tsv”)