def transferFeatures(hits): """ In table: feature_cvterm RILEY /class genedb_products /product In table: featureprop EC_number /EC_number colour /colour gene /gene """ # Connect to geneDB as read only user using ropy.query query = ropy.query.QueryProcessor(connection=connectionFactory) query.setSQLFilePath(os.path.dirname(__file__) + "/sql/") for hit in hits: # Extract all cvterm related to a feature_id from feature_cvterm table query.addQueryFromFile("feature_cvterm_query", "get_cvterm_from_feature_cvterm.sql") feature_cvterm_rows = query.runQuery("feature_cvterm_query", (hits[hit],)) logger.debug("--- %s" % hit) logger.debug('/ortholog="%s"' % hits[hit]) for row in feature_cvterm_rows: cvterm_name = row[0] cv_name = row[1] if cv_name == "RILEY": logger.debug('/class="%s"' % (cvterm_name)) elif cv_name == "genedb_products": logger.debug('/product="%s"' % (cvterm_name)) # Extract all cvterm relected to a feature_id from featureprop query.addQueryFromFile("featureprop_query", "get_cvterm_from_featureprop.sql") featureprop_rows = query.runQuery("featureprop_query", (hits[hit],)) for row in featureprop_rows: logger.debug('/%s="%s"' % (row[0], row[1])) logger.info("Features transfered")
def explanation_serving_t(train_df): data = {'vigil_t': [], 'explanation_serving_time': [], 'l1': [], 'l2': []} X_train = train_df[['x', 'y', 'x_range', 'y_range']].values y_train = train_df['count'].values sc = StandardScaler() sc.fit(X_train) X_train = sc.transform(X_train) #Training Models logger.info("Model Training Initiation\n=====================") kmeans = KMeans(random_state=0) mars_ = Earth(feature_importance_type='gcv', ) vigilance_t = np.linspace(0.01, 3, Config.vigilance_t_frequency) for sens_t in vigilance_t: logger.info("Sensitivity Level {}".format(sens_t)) lsnr = PR(mars_, vigil_theta=sens_t) lsnr.fit(X_train, y_train) for i in range(5): q = train_df.iloc[i].values[:4].reshape(1, -1) q = sc.transform(q) start = time.time() m = lsnr.get_model(q) end = time.time() - start data['vigil_t'].append(sens_t) data['explanation_serving_time'].append(end) data['l1'].append(lsnr.get_number_of_l1()) data['l2'].append(lsnr.get_number_of_l2()) return data
def del_user(id_tg): user = Users.get_or_none(id_tg) if user: user.delete_by_id(id_tg) logger.info(f'Пользователь удален: {user} в {datetime.datetime.now()}') return True return False
def say_welcome(message): logger.info(f'</code>@{message.from_user.username}<code> ({message.chat.id}) used /start or /help') bot.send_message( message.chat.id, '<b>Hello! This is a telegram bot template written by <a href="https://github.com/otter18">otter18</a></b>', parse_mode='html' )
def __init__(self, ytid, chid, func_send, normal_msg=False, save=False, live=True, chat_folder="chat"): # main self.livechat = LiveChatAsync(ytid, callback=self.post) if chid: self.id = str(chid) + "." + ytid else: self.id = ytid # discord channel and post function self.chid = str(chid) self.send = func_send # pytchat parameters self.ytid = ytid self.normal_msg = normal_msg self.live = live # save the chat self.save = save self.folder = chat_folder + "/" if save: os.makedirs(self.folder, exist_ok=True) if not self.is_alive(): raise ValueError("Is not live") logger.info(self.id + " is added")
def fasta2embl(infasta): """ Transform sequence file format in fasta to embl using EMBOSS seqret Returns the name of created embl file """ util.checkFile(infasta) outembl = infasta.split(".")[0] + ".embl" """ Usage: seqret Online documentation: http://emboss.open-bio.org/wiki/Appdoc:Seqret Standard (Mandatory) qualifiers: [-sequence] seqall (Gapped) sequence(s) filename and optional format, or reference (input USA) [-outseq] seqoutall [<sequence>.<format>] Sequence set(s) filename and optional format (output USA) The basic USA syntax is one of: "file" "file:entry" "format::file" "format::file:entry" "database:entry" "database" "@file" """ # Create EMBOSS seqret command line cmd = "seqret -sequence fasta::%s -outseq embl::%s " % (infasta, outembl) # Call the subprocess using convenience method util.runProcess(cmd) logger.info("File", outembl, "created") return outembl
def load_state(self, **kwargs): if not os.path.exists(self.state_file): return logger.info(f"Read last state from {self.state_file}") for id in open("state"): id = id.strip() self.add_video(id.split('.')[1], id.split('.')[0], **kwargs)
async def on_ready(): logger.debug(client.guilds) logger.info(f"{client.user} has connected to Discord!") # Overwrite the post function after Discord client initized for v in chats.videos: v.send = discord_notify(int(v.chid)) await chats.main()
def add_user(id_tg, name, sub=False): user = Users.get_or_none(id_tg) if user: return user user = Users.create(telegram_id=id_tg, name=name, sub=sub) logger.info(f'Пользователь создан: {id_tg}-{name}, {user}') return user
def splitSeq(dir, embl, type): """ Split sequence into separate file based on CDS features into dir/ directory based on EMBOSS extractfeat Usage: extractfeat Online documentation: http://emboss.open-bio.org/wiki/Appdoc:Extractfeat Standard (Mandatory) qualifiers: [-sequence] seqall Sequence(s) filename and optional format, or reference (input USA) [-outseq] seqout [.] Sequence filename and optional format (output USA) Additional (Optional) qualifiers: -type string [*] By default every feature in the feature table is extracted. You can set this to be any feature type you wish to extract. See http://www.ebi.ac.uk/Services/WebFeat/ for a list of the EMBL feature types and see the Uniprot user manual in http://www.uniprot.org/manual/sequence_annotation for a list of the Uniprot feature types. The type may be wildcarded by using '*'. If you wish to extract more than one type, separate their names with the character '|', eg: *UTR | intron (Any string is accepted) -featinname boolean [N] To aid you in identifying the type of feature that has been output, the type of feature is added to the start of the description of the output sequence. Sometimes the description of a sequence is lost in subsequent processing of the sequences file, so it is useful for the type to be a part of the sequence ID name. If you set this to be TRUE then the name is added to the ID name of the output sequence. Associated qualifiers: "-outseq" associated qualifiers -ossingle2 boolean Separate file for each entry -ofdirectory2 string Output directory The basic USA syntax is one of: "file" "file:entry" "format::file" "format::file:entry" "database:entry" "database" "@file" """ util.checkFile(embl) # Create directory util.createDir(dir) cmd = "extractfeat -sequence embl::%s -type %s -featinname YES -outseq fasta:: -osextension2 ffn -ossingle2 Yes -osdirectory2 %s" % (embl, type, dir) util.runProcess(cmd) logger.info("Sequences extracted into %s" % dir)
def say_welcome(message): logger.info( f'</code>@{message.from_user.username}<code> ({message.chat.id}) used /start or /help' ) bot.send_message( message.chat.id, '<b>Коверкает слова. ' 'При добавлении в группу рандомно реагирует на сообщения с негативным смысловым окрасом.</b>', parse_mode='html')
def printMSPCrunch(fasta_hits, reciprocal_hits): """ Print an MSPCrunch format description of the reciprocal hit """ for reciprocal_key in reciprocal_hits.keys(): if fasta_hits.has_key(reciprocal_key): logger.info(fasta_hits[reciprocal_key]) logger.info("MSP Crunch extracted")
async def on_message(message): # Only read command exclude bot itself if message.author == client.user: return if not message.content.startswith(".synchat"): return # if no args if not message.content.startswith(".synchat "): await message.channel.send("```" + parser.format_help() + "```") return # read command and videoid logger.debug(message.content) try: args = parser.parse_args(message.content.split()[1:]) except BaseException as e: # Fix this in Python3.9 logger.warning(str(type(e)) + str(e)) await message.channel.send("```" + parser.format_help() + "```") return method, id = args.method, args.id dc_channel = message.channel.id # list monitor list if method == "list": ids = [v.ytid for v in chats.videos if v.chid == str(dc_channel)] await message.channel.send("sync list: " + ",".join(ids)) return # id cannot be null if user wants to start or stop the chat if id is None: await message.channel.send("Fail: No video ID provieded") return # start to monitor if method == "start": logger.info(f"Sync {id} to {dc_channel}") if chats.add_video(id, dc_channel, discord_notify(dc_channel), save=True, chat_folder=chat_folder): await message.channel.send(f"OK {id}") else: await message.channel.send(f"Fail to add {id}") # stop monitor elif method == "stop": ok = await chats.remove_video(id, dc_channel) if ok: await message.channel.send("OK") else: await message.channel.send(f"No {id} found") else: await message.channel.send(f"{method} not implemented")
def echo(message): for t, resp in dialog.items(): if sum([e in message.text.lower() for e in resp['in']]): logger.info(f'</code>@{message.from_user.username}<code> ({message.chat.id}) used {t}:\n\n%s', message.text) bot.send_message(message.chat.id, random.choice(resp['out'])) return logger.info(f'</code>@{message.from_user.username}<code> ({message.chat.id}) used echo:\n\n%s', message.text) bot.send_message(message.chat.id, message.text)
def print_samples(sh): """Compactly print out contents of a SampleHandler""" logger.info('Number of samples: %i', len(sh)) for s in sh: logger.info('Sample: %s', s.name()) numFiles = s.numFiles() logger.info(' Number of files: %i', numFiles) logger.info(' Number of events: %i', s.getNumEntries()) for i in range(numFiles): logger.info(' %s', s.fileName(i))
def concatSeq(genome_file, dir): """ Concatenate separated CDS sequence fasta files located in dir into one file """ util.checkDir(dir) if os.path.exists(genome_file): os.remove(genome_file) cmd = "cat %s/*.faa > %s" % (dir, genome_file) util.runProcess(cmd) logger.info("concatSeq finished")
def runFasta(seq_dir, genomes_dir, fasta_dir): """ Run FASTA on protein sequences between new genome against all in house genomes FASTA searches a protein or DNA sequence data bank version 35.04 Aug. 25, 2009 W.R. Pearson & D.J. Lipman PNAS (1988) 85:2444-2448 """ util.createDir(fasta_dir) # List of in-house genomes util.checkDir(genomes_dir) genome_files = [] logger.info("Create fasta results directory for each in-house reference genome") for genome_file in os.listdir(genomes_dir): if '.faa' in genome_file: genome_files.append(genome_file) # Create fasta results directory for each in-house genome util.createDir("%s/%s" % (fasta_dir, genome_file.split(".")[0])) logger.info(genome_file) util.checkDir(seq_dir) if IS_LSF: # Rename new genome sequences for job array to be mygenome_1.faa mygenome_2.faa ... seq_num = 0 for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue seq_num += 1 if 'mygenome_' in seq_file and '.faa' in seq_file: continue seq_newfilepath = "%s/mygenome_%s.faa" % (seq_dir, seq_num) seq_filepath = "%s/%s" % (seq_dir, seq_file) os.rename(seq_filepath, seq_newfilepath) # Submit bsub job array on mygenome_${LSB_JOBINDEX}.faa against one refgenome at a time bsub_dir = "bsub" util.checkDir(bsub_dir) for genome_file in genome_files: res_dir = "%s/%s" % (fasta_dir, genome_file.split(".")[0]) cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/mygenome_${LSB_JOBINDEX}.faa %s/%s > %s/mygenome_${LSB_JOBINDEX}.fa" % (seq_dir, genomes_dir, genome_file, res_dir) util.submitJobArray(jobname="genepy-fasta", jobnum=seq_num, jobdir=bsub_dir, cmd=cmd) util.submitJobDependency('genepy-fasta') logger.info("Fasta on LSF finished") else: # List of new genome sequences for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue res_file = seq_file.split(".")[0] + ".fa" for genome_file in genome_files: res_dir = "%s/%s" % (fasta_dir, genome_file.split(".")[0]) cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/%s %s/%s > %s/%s" % (seq_dir, seq_file, genomes_dir, genome_file, res_dir, res_file) util.runProcess(cmd) logger.info(seq_file) logger.info("Fasta finished")
def __preprocessing_theta(self, vigil=.4): import warnings warnings.filterwarnings('ignore') #For each cluster for j in self.data_in_clusters_L1: #-2 Since each vector is made up of x\inR^d and y X = self.data_in_clusters_L1[ j][:, self.d // 2:-1] #Only care about clustering thetas logger.info("Shape of theta vector {}".format(X.shape)) c = 1 if (X.shape[0] > 10): # raise ValueError("Error in support of cluster") #Tuning k-parameter for kmeans c = 0 prev_inertia = 0 init = True diff = np.inf while diff >= vigil: logger.info("Current diff {0}/{1}".format(diff, vigil)) c += 1 t_kmeans = KMeans(n_clusters=c, random_state=0) t_kmeans.fit(X) pres_inertia = t_kmeans.inertia_ if not init: diff = np.abs(prev_inertia - pres_inertia) prev_inertia = pres_inertia else: prev_inertia = pres_inertia init = False if np.unique(t_kmeans.labels_).shape[0] != len( t_kmeans.cluster_centers_): print("Cluster {0}".format(j)) c = c - 1 logger.info("Number of clusters in thetas {}".format(c)) # #End of tuning CLUSTERS = c t_kmeans = KMeans(n_clusters=CLUSTERS, random_state=0) t_kmeans.fit(X) for i in range(CLUSTERS): mask = np.where(t_kmeans.labels_ == i)[0] logger.info("Data shape in cluster L1 {}, L2 {} : {}".format( j, i, self.data_in_clusters_L1[j][mask].shape)) self.data_in_clusters_L2[( j, i)] = self.data_in_clusters_L1[j][mask] self.THETA_CENTERS[j] = t_kmeans.cluster_centers_ logger.info("Shape of theta clusters in L1 {} : {}".format( j, self.THETA_CENTERS[j].shape))
def training_time(train_df): initial = train_df.head(10000) part = train_df.head(5000) data = {'size': [], 'time': [], 'l1': [], 'l2': []} for i in range(10): initial = pd.concat([initial, part]) for j in range(10): t, l1, l2 = execution_time(part) data['size'].append(initial.count()[0]) data['time'].append(t) data['l1'].append(l1) data['l2'].append(l2) logger.info("Loop {}/100".format(j + 10**i)) return data
def translateSeq(dir): """ Translate nucleic acid sequence in fasta format into protein sequence using EMBOSS transeq Usage: transeq Online documentation: http://emboss.open-bio.org/wiki/Appdoc:Transeq Standard (Mandatory) qualifiers: [-sequence] seqall Nucleotide sequence(s) filename and optional format, or reference (input USA) [-outseq] seqoutall [.] Protein sequence set(s) filename and optional format (output USA) Additional (Optional) qualifiers: -table menu [0] Code to use (Values: 0 (Standard); 1 (Standard (with alternative initiation codons)); 2 (Vertebrate Mitochondrial); 3 (Yeast Mitochondrial); 4 (Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma); 5 (Invertebrate Mitochondrial); 6 (Ciliate Macronuclear and Dasycladacean); 9 (Echinoderm Mitochondrial); 10 (Euplotid Nuclear); 11 (Bacterial); 12 (Alternative Yeast Nuclear); 13 (Ascidian Mitochondrial); 14 (Flatworm Mitochondrial); 15 (Blepharisma Macronuclear); 16 (Chlorophycean Mitochondrial); 21 (Trematode Mitochondrial); 22 (Scenedesmus obliquus); 23 (Thraustochytrium Mitochondrial)) The basic USA syntax is one of: "file" "file:entry" "format::file" "format::file:entry" "database:entry" "database" "@file" """ util.checkDir(dir) for file in os.listdir(dir): if '.ffn' in file: infasta = file outpep = file.split(".")[0] + ".faa" cmd = "transeq -sequence fasta::%s/%s -outseq fasta::%s/%s -table 11" % (dir, infasta, dir, outpep) util.runProcess(cmd) logger.info("Sequences translated.")
def execution_time(train_df): X_train = train_df[['x', 'y', 'x_range', 'y_range']].values y_train = train_df['count'].values sc = StandardScaler() sc.fit(X_train) X_train = sc.transform(X_train) #Training Models logger.info("Model Training Initiation\n=====================") kmeans = KMeans(random_state=0) mars_ = Earth(feature_importance_type='gcv', ) lsnr = PR(mars_, vigil_x=0.01) start = time.time() lsnr.fit(X_train, y_train) return (time.time() - start, lsnr.get_number_of_l1(), lsnr.get_number_of_l2())
def getHits(fasta_hits, reciprocal_hits): """ Return two dictionaries of ortholog hits and similarity hits containing {'new_genome_CDS_name':inhouse_genome_feature_id} """ ortholog_hits = {} for reciprocal_key in reciprocal_hits.keys(): if fasta_hits.has_key(reciprocal_key): ortholog_hits[reciprocal_key.split("||")[0]] = reciprocal_key.split("||")[1] del fasta_hits[reciprocal_key] similarity_hits = {} for fasta_key in fasta_hits: new_genome_key = fasta_key.split("||")[0] if not ortholog_hits.has_key(new_genome_key): similarity_hits[new_genome_key] = fasta_key.split("||")[1] return {'ortholog':ortholog_hits, 'similarity':similarity_hits} logger.info("Hits processed")
def __fit_models(self): #Fit an Earth model for each cluster for l1, l2 in self.data_in_clusters_L2: tcluster = self.data_in_clusters_L2[(l1, l2)] XX = tcluster[:, :self.d] logger.info("Shape of Training data {}".format(XX.shape)) yy = tcluster[:, -1] try: estimator = deepcopy(self.learning_algorithm) # model = Earth(max_degree=1, feature_importance_type='gcv') estimator.fit(XX, yy) except ValueError as e: print((i, j)) print(e) raise ValueError self.final_product[(l1, l2)] = estimator
def concatFeatures(embl, features): """ Concat CDS features in embl format into embl sequence file - the first two lines of embl sequence containing ID & XX lines - the CDS features file containing FT lines - the rest of embl sequence containing SQ lines Returns the name of created embl sequence file """ util.checkFile(embl) util.checkFile(features) outembl = embl.split(".")[0] + "_with_cds.embl" # Create command line head_cmd = "head -2 %s > %s; cat %s >> %s;" % (embl, outembl, features, outembl) util.runProcess(head_cmd) tail_cmd = "tail +3 %s > tail; cat tail >> %s; rm tail;" % (embl, outembl) util.runProcess(tail_cmd) logger.info("File", outembl, "created") return outembl
def execution_varying(train_df, L1, L2): X_train = train_df[['x', 'y', 'x_range', 'y_range']].values y_train = train_df['count'].values sc = StandardScaler() sc.fit(X_train) X_train = sc.transform(X_train) #Training Models logger.info("Model Training Initiation\n=====================") split = int(X_train.shape[0] / (L1 * L2)) mars_ = Earth() start = time.time() kmeans = KMeans(n_clusters=L1, random_state=0) kmeans.fit(X_train[:, :2]) l2_kmeans = KMeans(n_clusters=L2, random_state=0) for _ in range(L1): l2_kmeans.fit(X_train[:, 2:]) for _ in range(L2): mars_.fit(X_train[:split, :], y_train[:split]) return (time.time() - start)
def splitSeqWithBiopython(embl, type): """ Split sequence into separate file based on CDS features into sequences/ directory using Biopython """ util.checkFile(embl) # Create directory sequences/ dirname = "sequences/" util.createDir(dirname) record = SeqIO.read(open(embl, "rU"), "embl") if len(record.features) == 0: sys.exit("ERROR: EMBL file %s without features" % embl) for feature in record.features: if feature.type == 'CDS': seq = record.seq # Build up a list of (start,end) tuples that will be used to slice the sequence locations = [] # If there are sub_features, then this gene is made up of multiple parts. if len(feature.sub_features): for sf in feature.sub_features: locations.append((sf.location.start.position, sf.location.end.position)) # This gene is made up of one part. Store its start and end position. else: locations.append((feature.location.start.position, feature.location.end.position)) # Store the joined sequence and nucleotide indices forming the CDS. seq_str = '' for begin, end in locations: seq_str += seq[begin:end].tostring() # Reverse complement the sequence if the CDS is on the minus strand if feature.strand == -1: seq_obj = Seq(seq_str, IUPAC.ambiguous_dna) seq_str = seq_obj.reverse_complement().tostring() logger.debug(feature) logger.debug(SeqRecord(seq=Seq(seq_str), id=feature.qualifiers['systematic_id'][0], description=feature.type).format('fasta')) logger.info("Sequences extracted into %s" % dirname)
def topReciprocalFastaHits(res_dir): """ Extract top hits that cover at least 80% of the length of both sequences with at least 30% identity. Returns a dictionary of hits """ # Identity cutoff for reciprocal searches ident_cutoff = 0.3; # Length of hit cutoff for reciprocal searches len_cutoff = 0.8; # TODO Create MSP crunch file # Top hits dictionnary fastahits_dict = {} # Loop over the fasta results util.checkDir(res_dir) for (path, dirs, files) in os.walk(res_dir): for file in files: if not '.fa' in file: continue res_file = path + "/" + file logger.info("Reading... " + res_file) # Read the fasta alignment results with biopython AlignIO fasta-m10 alignments = AlignIO.parse(open(res_file), "fasta-m10", seq_count=2) for alignment in alignments: # Select the hit based on cutoffs if float(alignment._annotations["sw_ident"]) < ident_cutoff: continue record_query = alignment[0] record_match = alignment[1] overlap = float(alignment._annotations["sw_overlap"]) if overlap/float(record_query.annotations["original_length"]) < len_cutoff and overlap/float(record_match.annotations["original_length"]) < len_cutoff: continue record_query_region = "%s-%s" % (record_query._al_start, record_query._al_stop) record_match_region = "%s-%s" % (record_match._al_start, record_match._al_stop) # add hit into dictionnary key = "%s||%s" % (record_match.id, record_query.id) # inverted key to be comparable with fasta hits value = "%s %s %s %s %s %s" % (alignment._annotations["sw_score"], alignment._annotations["sw_ident"], record_query_region, record_query.id, record_match_region, record_match.id) fastahits_dict[key] = value logger.info("Extract reciprocal fasta alignment hits finished") return fastahits_dict
def chadoDump(dir): """ Dump the polypeptide sequences of all organisms stored in geneDB/chado in FASTA format """ util.createDir(dir) # Connect to geneDB as read only user using ropy.query query = ropy.query.QueryProcessor(connection=connectionFactory) query.setSQLFilePath(os.path.dirname(__file__) + "/sql/") # List of organisms query.addQueryFromFile("organism_query", "get_all_organisms_with_polyseq.sql") organism_rows = query.runQuery("organism_query") logger.info("Extracting %s organism sequences from geneDB. Please wait..." % len(organism_rows)) # Add fasta query query.addQueryFromFile("fasta_query", "get_fasta_polyseq_for_organism.sql") for organism in organism_rows: organism_name = organism[1] organism_id = organism[0] if organism_name == "dummy": continue # Dump sequence of each organism into a fasta file logger.info("Extracting %s..." % organism_name) fasta_rows = query.runQuery("fasta_query", (organism_id, )) file_path = "%s/%s_%s.faa" % (dir, organism_id, organism_name) out = open(file_path, 'w') for row in fasta_rows: if not row[0] == None: out.write(row[0]) out.write("\n") out.close() logger.info(" ...sequence extracted into %s." % file_path)
def runHamapScan(seq_dir, hamap_dir): """ HAMAP: High-quality Automated and Manual Annotation of microbial Proteomes ftp download site: ftp://ftp.expasy.org/databases/hamap/ pfscan compares a protein or nucleic acid sequence against a profile library. The result is an unsorted list of profile-sequence matches. download site: http://www.isrec.isb-sib.ch/ftp-server/pftools/pft2.3/ """ util.createDir(hamap_dir) util.checkDir(seq_dir) hamap_profile_file = "%s/hamap/hamap.prf" % os.path.dirname(__file__) if IS_LSF: # Rename new genome sequences for job array to be mygenome_1.faa mygenome_2.faa ... seq_num = 0 for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue seq_num += 1 if 'mygenome_' in seq_file and '.faa' in seq_file: continue seq_newfilepath = "%s/mygenome_%s.faa" % (seq_dir, seq_num) seq_filepath = "%s/%s" % (seq_dir, seq_file) os.rename(seq_filepath, seq_newfilepath) # Submit bsub job array on mygenome_${LSB_JOBINDEX}.faa against hamap profile bsub_dir = "bsub" util.checkDir(bsub_dir) cmd = "pfscan -klf %s/mygenome_${LSB_JOBINDEX}.faa %s > %s/mygenome_${LSB_JOBINDEX}.out" % (seq_dir, hamap_profile_file, hamap_dir) util.submitJobArray(jobname='genepy-hamap', jobnum=seq_num, jobdir=bsub_dir, cmd=cmd) util.submitJobDependency('genepy-hamap') logger.info("HAMAP scan on LSF finished") else: # List of new genome sequences for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue res_file = seq_file.split(".")[0] + ".out" cmd = "pfscan -klf %s/%s %s > %s/%s" % (seq_dir, seq_file, hamap_profile_file, hamap_dir, res_file) util.runProcess(cmd) logger.info("HAMAP scan finished")
def __preprocessing_x(self, X, y, vigil=.05): # #Tuning k-parameter for kmeans c = 0 prev_inertia = 0 pres_inertia = 0 init = True diff = np.inf X_ = X[:, :self.d // 2] logger.info("Shape of X in preprocessing x is : {}".format(X_.shape)) while diff >= vigil: logger.info("Current diff {0}/{1}".format(diff, vigil)) c += 1 kmeans = KMeans(n_clusters=c, random_state=0) kmeans.fit(X_) pres_inertia = kmeans.inertia_ if not init: diff = np.abs(prev_inertia - pres_inertia) prev_inertia = pres_inertia else: prev_inertia = pres_inertia init = False # #End of tuning logger.info("Number of clusters in X : {}".format(c)) CLUSTERS = c kmeans = KMeans(n_clusters=CLUSTERS) kmeans.fit(X_) #Assigning to clusters for i in np.unique(kmeans.labels_): mask = np.where(kmeans.labels_ == i) self.data_in_clusters_L1[i] = np.column_stack((X[mask], y[mask])) logger.info("Data shape in cluster {} : {}".format( i, self.data_in_clusters_L1[i].shape)) self.CLUSTER_CENTERS = kmeans.cluster_centers_ logger.info("Cluster centers shape {}".format( self.CLUSTER_CENTERS.shape))
def topFastaHits(res_dir, extractedseq_dir): """ Extract top fasta alignment hits that cover at least 80% of the length of both sequences with at least 30% identity. Creates an in-house fasta sequence file for each hit Returns a dictionnary of hits """ # Identity cutoff for reciprocal searches ident_cutoff = 0.3; # Length of hit cutoff for reciprocal searches len_cutoff = 0.8; # Extracted sequence directory util.createDir(extractedseq_dir) # TODO Create MSP crunch file # Top hits dictionnary fastahits_dict = {} # Loop over the fasta results util.checkDir(res_dir) for (path, dirs, files) in os.walk(res_dir): for file in files: if not '.fa' in file: continue res_file = path + "/" + file logger.info("Reading... " + res_file) # Read the fasta alignment results with biopython AlignIO fasta-m10 alignments = AlignIO.parse(open(res_file), "fasta-m10", seq_count=2) for alignment in alignments: # Select the hit based on cutoffs if float(alignment._annotations["sw_ident"]) < ident_cutoff: continue record_query = alignment[0] record_match = alignment[1] overlap = float(alignment._annotations["sw_overlap"]) if overlap/float(record_query.annotations["original_length"]) < len_cutoff and overlap/float(record_match.annotations["original_length"]) < len_cutoff: continue # Create SeqRecord of selected hit extractedseq_record = SeqRecord(seq=Seq(str(record_match.seq).replace('-', '')), id=record_match.id, description=res_file) extractedseq_file = "%s/%s.faa" % (extractedseq_dir, record_match.id) # Print match sequence of selected hit into fasta file output_handle = open(extractedseq_file, "w") SeqIO.write([extractedseq_record], output_handle, "fasta") output_handle.close() logger.info(" ...sequence extracted into %s" % extractedseq_file) record_query_region = "%s-%s" % (record_query._al_start, record_query._al_stop) record_match_region = "%s-%s" % (record_match._al_start, record_match._al_stop) # add hit into dictionnary key = "%s||%s" % (record_query.id, record_match.id) # value in MSP crunch format value = "%s %s %s %s %s %s" % (alignment._annotations["sw_score"], alignment._annotations["sw_ident"], record_query_region, record_query.id, record_match_region, record_match.id) fastahits_dict[key] = value logger.info("Extract fasta alignment hits finished") return fastahits_dict
def generate_subqueries_for_files(): directory = os.fsencode('input/Crimes_Workload') for file in os.listdir(directory): filename = os.fsdecode(file) if filename.startswith('test') and 'subqueries_{}'.format(filename) not in existing: logger.info("Loading Workload : {}".format(filename)) df = pd.read_csv('input/Crimes_Workload/{}'.format(filename), index_col=0) global std std = df[['x','y','x_range','y_range']].std().values pertubations = Parallel(n_jobs=4, verbose=2)(delayed(get_pertubations)(sq) for sq in df.values[:1000,:]) pertubations = np.array(pertubations) logger.info("Saving file {}".format(filename)) np.save('input/Subqueries/subqueries_{}'.format(filename),pertubations) else: logger.info("Skipping {}".format(filename))
def runReciprocalFasta(seq_dir, genome_file, fasta_dir): """ Run FASTA between extracted in-house protein sequences against new genome FASTA searches a protein or DNA sequence data bank version 35.04 Aug. 25, 2009 W.R. Pearson & D.J. Lipman PNAS (1988) 85:2444-2448 """ util.createDir(fasta_dir) # Check new genome util.checkFile(genome_file) # Check ref genome extracted sequences util.checkDir(seq_dir) res_dir = fasta_dir if IS_LSF: # Rename new genome sequences for job array to be refgenome_1.faa refgenome_2.faa ... seq_num = 0 for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue seq_num += 1 if 'refgenome_' in seq_file and '.faa' in seq_file: continue seq_newfilepath = "%s/refgenome_%s.faa" % (seq_dir, seq_num) seq_filepath = "%s/%s" % (seq_dir, seq_file) os.rename(seq_filepath, seq_newfilepath) # Submit bsub job array on refgenome_${LSB_JOBINDEX}.faa against mygenome bsub_dir = "bsub" util.checkDir(bsub_dir) cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/refgenome_${LSB_JOBINDEX}.faa %s > %s/refgenome_${LSB_JOBINDEX}.fa" % (seq_dir, genome_file, res_dir) util.submitJobArray(jobname="genepy-recipfasta", jobnum=seq_num, jobdir=bsub_dir, cmd=cmd) util.submitJobDependency('genepy-recipfasta') logger.info("Reciprocal Fasta on LSF finished") else: # List of inhouse extracted genome sequences for seq_file in os.listdir(seq_dir): if not '.faa' in seq_file: continue res_file = seq_file.split(".")[0] + ".fa" cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/%s %s > %s/%s" % (seq_dir, seq_file, genome_file, res_dir, res_file) util.runProcess(cmd) logger.info(seq_file) logger.info("Reciprocal Fasta finished")
def load_data(): logger.info("Loading Data...") data = pd.read_csv('input/Crimes_-_2001_to_present.csv', header=0) global dd dd = data[['X Coordinate', 'Y Coordinate', 'Arrest', 'Beat']]
async def console_print(c): if type(c) is str: logger.info(c) else: logger.debug(f"Print data: {str(c.json())}")
async def close(self): logger.info(self.id + " to stopped") await self.send(f"{self.ytid} is stopped") self.livechat.terminate()
def show_status(self): logger.info("check: " + ",".join([i.id for i in self.videos])) # save state to file if self.state: self.write_state()
parser.add_argument("--verbose", dest='verbosity', help="increase output verbosity", action="store_true") parser.add_argument('-v', help='verbosity', dest='verbosity', action="store_true") args = parser.parse_args() if args.verbosity: print("verbosity turned on") handler = logging.StreamHandler(sys.stdout) handler.setLevel(logging.DEBUG) logger.addHandler(handler) if not os.path.exists('output/Accuracy'): logger.info('creating directory Accuracy') os.makedirs('output/Accuracy') def kl_divergence_error(y, y_hat): kd = KernelDensity(bandwidth=0.75).fit(y.reshape(-1, 1)) yp = kd.score_samples(y.reshape(-1, 1)) kd = KernelDensity(bandwidth=0.75).fit(y_hat.reshape(-1, 1)) ypg = kd.score_samples(y_hat.reshape(-1, 1)) return entropy(yp, ypg) def model_based_divergence(X, y, model_2): model_1 = Earth(feature_importance_type='gcv') model_1.fit(X, y) features_l = model_1.feature_importances_
import logging import sys from setup import logger from PyQt5 import QtWidgets from app.main_window import MainWindow from db import db if __name__ == "__main__": logger.setLevel(logging.DEBUG) logger.info('App start') app = QtWidgets.QApplication(sys.argv) main_window = None try: db.connect() db.create_tables([]) # fixme main_window = MainWindow(app) main_window.show() sys.exit(app.exec()) except Exception as e: logger.exception(e) finally: db.close() # todo check if main_window: main_window.stop() logger.info('App close')
import pandas as pd import numpy as np import os import sys os.chdir("../../../explanation_framework") sys.path.append("../explanation_framework") sys.path.append('utils') from terminal_outputs import printProgressBar from confs import Config from setup import logger from joblib import Parallel, delayed if not os.path.exists('input/Subqueries'): logger.info('creating directory Subqueries') os.makedirs('input/Subqueries') existing = set(os.listdir('input/Subqueries')) DIM = 2 NSUBQUERIES = Config.NSUBQUERIES def load_data(): logger.info("Loading Data...") data = pd.read_csv('input/Crimes_-_2001_to_present.csv', header=0) global dd dd = data[['X Coordinate', 'Y Coordinate', 'Arrest', 'Beat']] def vectorize_query(q): # res = dd_matrix[np.all((dd_matrix[:,:2]>q[:,:DIM]-q[:,DIM:2*DIM]) & (dd_matrix[:,:2]<q[:,:DIM]+q[:,DIM:2*DIM]),axis=1)] res = dd[(dd['X Coordinate']>float(q[:,0]-q[:,2])) & (dd['X Coordinate']<float(q[:,0]+q[:,2])) & (dd['Y Coordinate']>float(q[:,1]-q[:,3])) & (dd['Y Coordinate']<float(q[:,1]+q[:,3]))].values return np.array([res.shape[0], np.sum(res[:,2]),np.mean(res[:,3])]) if res.shape[0]!=0 else np.zeros(3)
def main(): # Fasta file extension: # .ffn for the untranslated nucleotide sequences for each CDS; .faa for protein coding sequences (CDS) # .fa for the fasta alignment results # .fna for whole genomic DNA sequences; .frn for nucleotide sequences of RNA related features usage = "usage: %prog [Options]" parser = OptionParser(usage=usage) parser.add_option("-d", "--dna", metavar="FILE", help="input dna FILE in fasta format", action="store", type="string", dest="dna") parser.add_option("-t", "--tab", metavar="FILE", help="input tab FILE in embl format", action="store", type="string", dest="tab") parser.add_option("-e", "--embl", metavar="FILE", help="input embl FILE with CDS features in embl format", action="store", type="string", dest="embl") parser.add_option("--genedb", help="extract reference genome protein sequences from geneDB", action="store_true", dest="db") parser.add_option("--fasta", help="run fasta against each extracted in-house genomes", action="store_true", dest="fasta") parser.add_option("--hamap", help="run pfscan against HAMAP profiles", action="store_true", dest="hamap") parser.add_option("--clean", help="delete all results without deleting reference genomes", action="store_true", dest="clean") parser.add_option("--deepclean", help="delete all reference genomes and results", action="store_true", dest="deepclean") (options, args) = parser.parse_args() # Print help if no argument given if util.printHelp(options): parser.print_help() sys.exit() # Print command line cmdline = "$ python " for argv in sys.argv: cmdline += argv + " " logger.debug(cmdline) # >>> --------------------------------------------------------------------- # >>> DATA PREPARATION # >>> --------------------------------------------------------------------- # List of needed software for softname in soft_lists: util.checkSoft(softname) # Prepare new genome data if options.dna and options.tab and not options.embl: util.checkFile(options.dna) mygenome_emblfile = fasta2embl(options.dna) mygenome_emblfile_withcds = concatFeatures(mygenome_emblfile, options.tab) splitSeq(mygenome_dir, mygenome_emblfile_withcds, "CDS") translateSeq(mygenome_dir) elif not options.dna and not options.tab and options.embl: mygenome_emblfile_withcds = options.embl splitSeq(mygenome_dir, mygenome_emblfile_withcds, "CDS") #splitSeqWithBiopython(mygenome_emblfile_withcds, "CDS") # does not work with testdata_01 translateSeq(mygenome_dir) elif not options.deepclean: util.checkDir(mygenome_dir) # Extract in house genomes from chado db if options.db: chadoDump(refgenomes_dir) elif not options.deepclean: util.checkDir(refgenomes_dir) # bsub output directory if IS_LSF and not (options.clean or options.deepclean): util.createDir(bsub_dir) # >>> --------------------------------------------------------------------- # >>> ORTHOLOG SEARCH # >>> --------------------------------------------------------------------- # Run fasta & reciprocal fasta if options.fasta: runFasta(mygenome_dir, refgenomes_dir, fasta_dir) fasta_hits = topFastaHits(fasta_dir, refgenomes_extractedseq_dir) concatSeq(mygenome_fastafile_allcds, mygenome_dir) runReciprocalFasta(refgenomes_extractedseq_dir, mygenome_fastafile_allcds, reciprocalfasta_dir) reciprocalfasta_hits = topReciprocalFastaHits(reciprocalfasta_dir) printMSPCrunch(fasta_hits, reciprocalfasta_hits) hits = getHits(fasta_hits, reciprocalfasta_hits) logger.info("ORTHOLOGS") logger.info(hits['ortholog']) logger.info("SIMILARITY") logger.info(hits['similarity']) transferFeatures(hits['ortholog']) # Run hamap scan if options.hamap: runHamapScan(mygenome_dir, hamap_dir) # >>> --------------------------------------------------------------------- # >>> CLEANING OUTPUT DATA # >>> --------------------------------------------------------------------- # Clean results before a re-run if options.clean: # fasta results util.rmDir(fasta_dir) util.rmDir(reciprocalfasta_dir) util.rmDir(refgenomes_extractedseq_dir) util.rmFile(mygenome_fastafile_allcds) # hamap results util.rmDir(hamap_dir) # bsub outputs if IS_LSF: util.rmDir(bsub_dir) # Deep clean - remove all if options.deepclean: util.rmDir(refgenomes_dir) util.rmDir(mygenome_dir) util.rmDir(fasta_dir) util.rmDir(reciprocalfasta_dir) util.rmDir(refgenomes_extractedseq_dir) util.rmFile(mygenome_fastafile_allcds) util.rmDir(hamap_dir)
def accuracy_on_crimes(): logger.info("Finding datasets...") directory = os.fsencode('input/Crimes_Workload') directory_sub = os.fsencode('input/Subqueries/') patterns = {'gauss-gauss': '*x-gauss*-length-gauss*', 'gauss-uni': '*x-gauss*-length-uniform*', 'uni-gauss': '*x-uniform*-length-gauss*', 'uni-uni': '*x-uniform*-length-uniform*',} train_datasets = {} test_datasets = {} sub_datasets = {} for p in patterns: res = [os.fsdecode(n) for n in os.listdir(directory) if fnmatch.fnmatch(os.fsdecode(n), patterns[p])] train_datasets[p] = res[0] if res[0].startswith('train') else res[1] test_datasets[p] = res[0] if res[0].startswith('test') else res[1] sub_datasets[p] = [os.fsdecode(n) for n in os.listdir(directory_sub) if fnmatch.fnmatch(os.fsdecode(n), patterns[p])][0] res_eval = {'model': [], 'dataset': [], 'aggregate_name': [], 'kl': [], 'r2':[], 'md':[], 'nrmse':[]} #Main for p in patterns: logger.info('Beginning Evaluation for {0}'.format(p)) logger.info('Loading Datasets...') test_df = pd.read_csv('/home/fotis/dev_projects/explanation_framework/input/Crimes_Workload/{0}'.format(test_datasets[p]), index_col=0) train_df = pd.read_csv('/home/fotis/dev_projects/explanation_framework/input/Crimes_Workload/{0}'.format(train_datasets[p]), index_col=0) sub = np.load('/home/fotis/dev_projects/explanation_framework/input/Subqueries/{0}'.format(sub_datasets[p])) logger.info('Finished loading\nCommencing Evaluation') aggregates = ['count','sum_','avg'] agg_map = {'count' :4, 'sum_':5, 'avg':6} for agg in aggregates: logger.info("Evaluating Aggregates : {0}".format(agg)) X_train = train_df[['x','y','x_range','y_range']].values y_train = train_df[agg].values sc = StandardScaler() sc.fit(X_train) X_train = sc.transform(X_train) #Training Models logger.info("Model Training Initiation\n=====================") kmeans = KMeans() lr = Ridge() lsnr = PR(lr) lsnr.fit(X_train,y_train) lr_global = LinearRegression() lr_global.fit(X_train, y_train) logger.info("Accuracy Evaluation on Test set\n=====================") for i in range(1000): #Obtain query from test-set dataset = p printProgressBar(i, 1000,prefix = 'Progress:', suffix = 'Complete', length = 50) q = test_df.iloc[i].values[:4].reshape(1,-1) q = sc.transform(q) #Obtain subquery pertubations for query q from test set q1 = sub[i] X = q1[:,:4] y = q1[:,agg_map[agg]] X = sc.transform(X) # Train local model (Should be the best out of the 3) lr = LinearRegression() lr.fit(X,y) y_hat = lr.predict(X) metrics_for_model('local',dataset,agg,y_hat,X, y, lr,res_eval) #Obtain metrics for our y_hat_s = lsnr.get_model(q).predict(X) metrics_for_model('ours',dataset,agg,y_hat_s,X,y,lsnr.get_model(q) ,res_eval) #Obtain metrics for global y_hat_g = lr_global.predict(X) metrics_for_model('global',dataset,agg,y_hat_g,X,y,lr_global,res_eval) logger.info("Finished Queries") eval_df = pd.DataFrame(res_eval) eval_df.to_csv('output/Accuracy/evaluation_results_linear.csv')
gattr_to_table_map = { key: value for key, value in zip(df['column_name'].values, df['table_name'].values) } print(gattr_to_table_map) #print(attrs_array) # attrs_dict = { key : [] for key in attrs_array } #dict.fromkeys(attrs_array,[[]]*len(attrs_array)) distinct_attr = {} i = 0 qdf = None j = 0 tot_query_answering_time = 0 start = time.time() for qname, q in queries: logger.info("Query :\n{}\n".format(q)) ####Execute Query and obtain result start_query = time.time() cur.execute(q) tot_query_answering_time += (time.time() - start_query) res = cur.fetchall() res_df = pd.DataFrame(res) res_df = res_df.set_index(np.arange(i, i + res_df.shape[0])) if res_df.empty: logger.debug("Query is empty") j += 1 continue pr = Parser() qv = QueryVectorizer(set(df['column_name'].tolist())) #Begin parsing the query and vectorizing its parameters pr.parse(q)
dest='verbosity', help="increase output verbosity", action="store_true") parser.add_argument('-v', help='verbosity', dest='verbosity', action="store_true") args = parser.parse_args() if args.verbosity: print("verbosity turned on") handler = logging.StreamHandler(sys.stdout) handler.setLevel(logging.DEBUG) logger.addHandler(handler) if not os.path.exists('output/Performance'): logger.info('creating directory Performance') os.makedirs('output/Performance') def execution_time(train_df): X_train = train_df[['x', 'y', 'x_range', 'y_range']].values y_train = train_df['count'].values sc = StandardScaler() sc.fit(X_train) X_train = sc.transform(X_train) #Training Models logger.info("Model Training Initiation\n=====================") kmeans = KMeans(random_state=0) mars_ = Earth(feature_importance_type='gcv', ) lsnr = PR(mars_, vigil_x=0.01)
parser.add_argument("--verbose", dest='verbosity', help="increase output verbosity", action="store_true") parser.add_argument('-v',help='verbosity',dest='verbosity',action="store_true") parser.add_argument("--crimes",dest="crimes", action="store_true") parser.add_argument("--higgs",dest="higgs", action="store_true") parser.add_argument("--accelerometer",dest="accelerometer", action="store_true") args = parser.parse_args() if args.verbosity: print("verbosity turned on") handler = logging.StreamHandler(sys.stdout) handler.setLevel(logging.DEBUG) logger.addHandler(handler) if not os.path.exists('output/Accuracy'): logger.info('creating directory Accuracy') os.makedirs('output/Accuracy') if not (args.crimes or args.higgs or args.accelerometer): logger.info("No data set specified") sys.exit() def kl_divergence_error(y, y_hat): kd = KernelDensity(bandwidth=0.75).fit(y.reshape(-1,1)) yp = kd.score_samples(y.reshape(-1,1)) kd = KernelDensity(bandwidth=0.75).fit(y_hat.reshape(-1,1)) ypg = kd.score_samples(y_hat.reshape(-1,1)) return entropy(yp,ypg) def model_based_divergence(X,y, model_2): model_1 = LinearRegression()# Earth(feature_importance_type='gcv')
def accuracy_on_higgs(): logger.info("Starting Accuracy Tests on Higgs") logger.info("================================") df = pd.read_csv('input/sample_higgs_0.01.csv', index_col=0) X = df[['m_bb','m_wwbb']].dropna().values y = df['label'] min_ = np.min(X, axis=0) max_ = np.max(X, axis=0) X = (X-min_) / (max_-min_) data = np.column_stack((X,y)) x = np.linspace(0.1,0.9,7) xx,yy = np.meshgrid(x,x) DIMS = X.shape[1] cov = np.identity(DIMS)*0.001 cluster_centers = np.column_stack((xx.ravel(),yy.ravel())) query_centers = [] #Generate queries over cluster centers for c in cluster_centers: queries = np.random.multivariate_normal(np.array(c), cov, size=40) query_centers.append(queries) query_centers = np.array(query_centers).reshape(-1,DIMS) ranges = np.random.uniform(low=0.005**(1/3), high=0.25**(1/3), size=(query_centers.shape[0], DIMS)) queries = [] empty = 0 for q,r in zip(query_centers,ranges): b = generate_boolean_vector(data,q,r,2) res = data[b] if res.shape[0]==0: empty+=1 ans = float(np.mean(res[:,-1])) if res.shape[0]!=0 else 0 qt = q.tolist() qt += r.tolist() qt.append(ans) queries.append(qt) qs = np.array(queries).reshape(-1, 2*DIMS+1) X_train, X_test, y_train, y_test = train_test_split( qs[:,:qs.shape[1]-1], qs[:,-1], test_size=0.4, random_state=0) earth = Earth() lsnr = PR(earth) lsnr.fit(X_train, y_train) y_hat = np.array([float(lsnr.get_model(x.reshape(1,-1)).predict(x.reshape(1,-1))) for x in X_test]) r2 = metrics.r2_score(y_test,y_hat) kl = kl_divergence_error(y_test, y_hat) nrmse = np.sqrt(metrics.mean_squared_error(y_test, y_hat))/np.mean(y_test) logger.info("R2 Score : {}\nNRMSE : {}\nKL-Divergence : {}".format(r2, nrmse, kl)) #Linear Regression comparsion lr = LinearRegression() lr.fit(X_train, y_train) y_hat_lr = lr.predict(X_test) r2_lr = metrics.r2_score(y_test, y_hat_lr) kl_lr = kl_divergence_error(y_test, y_hat_lr) nrmse_lr = np.sqrt(metrics.mean_squared_error(y_test, y_hat_lr))/np.mean(y_test) logger.info("R2 Score : {}\nNRMSE : {}\nKL-Divergence : {}".format(r2_lr, kl_lr, nrmse_lr)) dic = {} dic['LPM' ]= [('r2',r2), ('kl',kl), ('nrmse',nrmse)] dic['LR'] = [('r2',r2_lr), ('kl',kl_lr), ('nrmse',nrmse_lr)] #Polynomial regression comparsion for count, degree in enumerate(np.arange(3,10,2)): model = make_pipeline(PolynomialFeatures(degree), Ridge()) model.fit(X_train, y_train) y_hat = model.predict(X_test) r2_p = metrics.r2_score(y_test,y_hat) kl_p = kl_divergence_error(y_test, y_hat) nrmse_p = np.sqrt(metrics.mean_squared_error(y_test, y_hat))/np.mean(y_test) dic["LR ({})".format(degree)] = [('r2',r2_p), ('kl',kl_p), ('nrmse',nrmse_p)] print("R2 for degree {} : {}".format(degree, metrics.r2_score(y_test, y_hat))) logger.info("==============================================") with open('output/Accuracy/multiple_methods_higgs.pkl', 'wb') as handle: pickle.dump(dic, handle)