How to use str_matches method in pandera
Best Python code snippet using pandera_python
parser.py
Source:parser.py 
...11 file = pd.read_excel(file_path)12 error_schema = DataFrameSchema({13 "nom_amenageur": Column(str, Check.is_uppercase(), nullable=True),14 "siren_amenageur": Column(int, Check.in_range(100000000, 999999999)),15 "contact_amenageur": Column(str, Check.str_matches(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')),16 "nom_operateur": Column(str, nullable=True),17 "contact_operateur": Column(str, Check.str_matches(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')),18 "telephone_operateur": Column(str, nullable=True),19 "nom_enseigne": Column(str),20 "id_station_itinerance": Column(str, Check.str_matches(r'(?:(?:^|,)(^FR[A-Z0-9]{4,33}$|Non concerné))+$')),21 "id_station_local": Column(str, nullable=True),22 "nom_station": Column(str),23 "implantation_station": Column(str, Check.str_matches(24 r'(Voirie|Parking public|Parking privé à usage public|Parking privé réservé à la clientèle|Station dédiée à la recharge rapide){1}')),25 "adresse_station": Column(str),26 # "code_insee_commune": Column(str, Check.str_matches(r'^([013-9]\d|2[AB1-9])\d{3}$')),27 # Regex officiel code INSEE ne marche pas28 # coordonneesXY29 # Difficile à valider. consolidated_longitude et latitude sont elles validées.30 "nbre_pdc": Column(int, Check.greater_than(0)),31 "id_pdc_itinerance": Column(str, Check.str_matches(r'(?:(?:^|,)(^FR[A-Z0-9]{4,33}$|Non concerné))+$')),32 "id_pdc_local": Column(str, nullable=True),33 "puissance_nominale": Column(float, Check.greater_than_or_equal_to(0)),34 "prise_type_ef": Column(int, Check.in_range(0, 1)),35 "prise_type_2": Column(int, Check.in_range(0, 1)),36 "prise_type_combo_ccs": Column(int, Check.in_range(0, 1)),37 "prise_type_chademo": Column(int, Check.in_range(0, 1)),38 "prise_type_autre": Column(int, Check.in_range(0, 1)),39 "gratuit": Column(int, Check.in_range(0, 1)),40 "paiement_acte": Column(int, Check.in_range(0, 1)),41 "paiement_cb": Column(int, Check.in_range(0, 1)),42 "tarification": Column(str, nullable=True),43 "condition_acces": Column(str, Check.str_matches(r'(Accès libre|Accès réservé){1}')),44 "reservation": Column(int, Check.in_range(0, 1)),45 # "horaires": Column(str, Check.str_matches(r'(.*?)((\d{1,2}:\d{2})-(\d{1,2}:\d{2})|24/7)')),46 # Regex officielle ne marche pas47 "accessibilite_pmr": Column(str, Check.str_matches(48 r'(Réservé PMR|Accessible mais non réservé PMR|Non accessible|Accessibilité inconnue){1}')),49 "restriction_gabarit": Column(str),50 "station_deux_roues": Column(int, Check.in_range(0, 1)),51 "raccordement": Column(str, Check.str_matches(r'(Direct|Indirect){1}')),52 "num_pdl": Column(str, nullable=True),53 # date_mise_en_service54 # Dates, compliqué à valider55 "observations": Column(str, nullable=True),56 # date_maj57 # last_modified58 "datagouv_dataset_id": Column(str),59 "datagouv_resource_id": Column(str),60 "datagouv_organization_or_owner": Column(str),61 "consolidated_longitude": Column(float, Check.in_range(-180, 180)),62 "consolidated_latitude": Column(float, Check.in_range(-180, 180)),63 "consolidated_code_postal": Column(int, Check.in_range(1000, 99999)),64 "consolidated_commune": Column(str),65 "consolidated_is_lon_lat_correct": Column(int, Check.in_range(0, 1)),66 "consolidated_is_code_insee_verified": Column(int, Check.in_range(0, 1)),67 })68 warning_schema = DataFrameSchema({69 "contact_amenageur": Column(str, Check.str_matches(r'\b[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,}\b')),70 "contact_operateur": Column(str, Check.str_matches(r'\b[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,}\b')),71 "nom_amenageur": Column(str, Check.is_uppercase(), nullable=True),72 })73 error_percent = 074 warning_percent = 075 warning_df = pd.DataFrame()76 error_df = pd.DataFrame()77 try:78 error_schema.validate(file, lazy=True)79 except errors.SchemaErrors as err:80 pd.set_option("display.max_columns", None, "display.max_rows", None)81 error_df = err.failure_cases82 error_percent = len(err.failure_cases)/len(file)*10083 try:84 warning_schema.validate(file, lazy=True)...
preprocessing.py
Source:preprocessing.py
1import re2class PreProcessing():3 def __init__(self, raw_dict):4 self.raw_comp = raw_dict["Components"]5 self.raw_rules = raw_dict["Rules"]6 self.components = self.get_dict_components()7 self.rules = self.get_rules()8 def get_dict_components(self) -> dict:9 components = dict()10 matches_for_comp = self.get_matches_components()11 for key in matches_for_comp.keys():12 components[key] = matches_for_comp[key][0]13 if key == "States":14 components["Initial State"] = matches_for_comp[key][1]15 components["Final States"] = matches_for_comp[key][2]16 for key, value in components.items():17 components[key] = self.format_str(value)18 components["Initial State"] = components["Initial State"][0]19 return components20 def get_matches_components(self) -> dict:21 symb_pattern = re.compile(r"{([a-z],\s*)*[a-z]}")22 state_pattern = re.compile(r"(q(\d+|f),\s*)*q(\d+|f)")23 stack_symb_pattern = re.compile(r"{([A-Z],\s*)*[A-Z]}")24 patterns = {"Symbols": symb_pattern, "States": state_pattern, "Stack Symbols": stack_symb_pattern}25 matches_comps = dict()26 for key, value in patterns.items():27 matches_comps[key] = self.find(value)28 return matches_comps29 def find(self, pattern) -> list:30 str_matches = []31 matches = re.finditer(pattern, self.raw_comp)32 for match in matches:33 str_matches.append(match.group())34 return str_matches35 def format_str(self, string) -> list:36 string = string.replace("{", "")37 string = string.replace("}", "")38 lista = string.split(",")39 for i in range(len(lista)):40 lista[i] = lista[i].strip()41 return lista42 def get_rules(self) -> list:43 rules = []44 keys = ["origin_state", "word_read_symbol", "stack_read_symbol",45 "final_state", "stack_written_symbol"]46 for item in self.raw_rules:47 dict_rules = dict()48 for i in range(5):49 dict_rules[keys[i]] = self.format_str(item)[i]50 rules.append(dict_rules)51 """52 rules = []53 for item in self.raw_rules:54 rules.append(self.format_str(item))55 """...
dna.py
Source:dna.py
1import sys2import csv3def main():4 argc = len(sys.argv)5 # Check for incorrect usage6 if argc != 3:7 print("Usage: ./dna.py <db_file> <sequence_file>")8 sys.exit(1)9 else:10 db_file = sys.argv[1]11 sequence_file = sys.argv[2]12 # Get STRs and their consecutive occurences in sequence13 with open(db_file) as db_stream:14 db_csv = csv.reader(db_stream)15 STRs = next(db_csv)[1::]16 str_occurence = {}17 for i in range(len(STRs)):18 str_occurence[STRs[i]] = str_repetitions(STRs[i], sequence_file)19 # Get CSV database as a list of people20 with open(db_file) as db_stream:21 db_csv_dict = csv.DictReader(db_stream)22 people = []23 for row in db_csv_dict:24 people.append(row)25 # Check for matches of sequence STRs for each person in people26 for person in people:27 str_matches = 028 for str_ in STRs:29 if int(person[str_]) == str_occurence[str_]:30 str_matches += 131 if str_matches == len(STRs):32 print(person['name'])33 sys.exit(0)34 print("No match")35# Return the number of consecutive occurences of the STR (str_seq) in the Sequence file (seq_file)36def str_repetitions(str_sequence, sequence_file):37 str_length = len(str_sequence)38 repetitions = 039 consecutive_matches = 040 pos = 041 # Read sequence_file into a buffer string42 with open(sequence_file) as sequence_stream:43 buffer = sequence_stream.read()44 buffer_len = len(buffer)45 i = 046 while i < buffer_len:47 cc = buffer[i]48 i += 149 if cc == str_sequence[pos]:50 pos += 151 if pos == str_length:52 repetitions += 153 if repetitions > consecutive_matches:54 consecutive_matches = repetitions55 pos = 056 else:57 i = i - pos58 pos = 059 repetitions = 060 return consecutive_matches...
Automation Testing Tutorials
Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.
LambdaTest Learning Hubs:
- JUnit Tutorial
- TestNG Tutorial
- Webdriver Tutorial
- WebDriverIO Tutorial
- Protractor Tutorial
- Selenium 4 Tutorial
- Jenkins Tutorial
- NUnit Tutorial
- Jest Tutorial
- Playwright Tutorial
- Cypress Tutorial
- PyTest Tutorial
YouTube
You could also refer to video tutorials over LambdaTest YouTube channel to get step by step demonstration from industry experts.
Run pandera automation tests on LambdaTest cloud grid
Perform automation testing on 3000+ real desktop and mobile devices online.
Try LambdaTest Now !!
Get 100 minutes of automation test minutes FREE!!
Was this article helpful?
