-1
我想從pandas數據框中的文件中讀取雙串行化的json
對象。 的json
實施例是下面,在熊貓數據框中讀取序列化的json
{"input":"8\t140630920\t.\tC\tT\t840.948\t.","assembly_name":"GRCh37","end":140630920,"seq_region_name":"8","transcript_consequences":[{"source":"Ensembl","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"ENST00000520439","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"RefSeq","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"NM_016601.2","cds_start":706,"gene_id":51305,"protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"RefSeq","variant_allele":"T","cdna_end":764,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":764,"transcript_id":"XM_005250954.1","cds_start":706,"gene_id":51305,"protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"Ensembl","variant_allele":"T","cdna_end":755,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":755,"transcript_id":"ENST00000522317","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant","NMD_transcript_variant"],"impact":"MODERATE"},{"source":"Ensembl","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"ENST00000303015","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"gene_id":"ENSG00000169427","source":"Ensembl","distance":1672,"variant_allele":"T","phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"consequence_terms":["upstream_gene_variant"],"strand":-1,"transcript_id":"ENST00000523477","impact":"MODIFIER"},{"gene_id":"ENSG00000169427","source":"Ensembl","distance":2630,"variant_allele":"T","phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"consequence_terms":["upstream_gene_variant"],"strand":-1,"transcript_id":"ENST00000519923","impact":"MODIFIER"}],"strand":1,"id":"8_140630920_C/T","allele_string":"C/T","most_severe_consequence":"missense_variant","start":140630920}
使用大熊貓數據幀讀這篇文章,
dft = pd.read_json(filename, lines = True)
結果在表如下所示, Table generated by pandas read-json
然而,我想從提取信息['transcript_consequences']
列,也可從['phenotypes']
列出['transcript_consequences']
列。
如何在熊貓數據框中實現這個功能?
什麼是 「雙連載」 是什麼意思? –
@John Zwinck我給出了一個我想處理json的例子..hope有幫助。謝謝 – nilesh
@nilesh做了我的建議工作?與您的實際數據有什麼特別的區別? – erasmortg