import re
import time
from selenium.common.exceptions import NoSuchElementException
from datetime import datetime, timedelta
from log import log, log_to_file, get_file_log
from classes.match_status import MatchStatus
from managers.player_manager import add_player_info
from managers.tournament_manager import scrap_tournament, add_tournament_info, update_tournament, create_tournament
from queries.match_queries import q_find_match_by_id, q_update_match, q_create_match, q_delete_match, \
get_embedded_matches_json
from queries.tournament_queries import find_tournament_by_name
from utils import element_has_class, get_chrome_driver
MATCHES_LOGS = get_file_log("scrap_matches")
MATCHES_ERROR_LOGS = get_file_log("scrap_matches_error")
TOURNAMENT_LOGS = get_file_log("tournament_updates")
def get_match_dtypes(matches):
all_dtypes = {
"draw_size": "Int16", "best_of": "object", "minutes": "Int16", "p1_ht": "Int16", "p2_ht": "Int16",
"p1_weight": "Int16",
"p2_weight": "Int16", "p1_ace": "Int16", "p2_ace": "Int16", "p1_df": "Int16", "p2_df": "Int16",
"p1_svpt": "Int16", "p2_svpt": "Int16", "p1_1st_in": "Int16", "p2_1st_in": "Int16", "p1_1st_won": "Int16",
"p2_1st_won": "Int16", "p1_2nd_won": "Int16", "p2_2nd_won": "Int16", "p1_sv_gms": "Int16",
"p2_sv_gms": "Int16", "p1_bp_saved": "Int16", "p2_bp_saved": "Int16", "p1_bp_faced": "Int16",
"p2_bp_faced": "Int16", "p1_rank": "Int16", "p2_rank": "Int16", "p1_rank_points": "Int16",
"p2_rank_points": "Int16", "p1_s1_gms": "Int16", "p2_s1_gms": "Int16", "p1_tb1_score": "Int16",
"p2_tb1_score": "Int16", "p1_s2_gms": "Int16", "p2_s2_gms": "Int16", "p1_tb2_score": "Int16",
import time
import re
import pandas as pd
import json
from datetime import datetime
from selenium.common.exceptions import NoSuchElementException
from log import log, get_file_log, log_to_file
from managers.player_rank_manager import retrieve_player_rank_info
from queries.country_queries import country_exists, find_country_with_flag_code
from queries.player_queries import find_player_by_id, q_create_player, q_update_player
from utils import get_chrome_driver
PLAYER_LOGS = get_file_log("scrap_player")
def scrap_player_id(player_name):
atptour_name = atptour_id = None
driver = get_chrome_driver()
match_url = 'https://www.atptour.com/en/-/ajax/playersearch/PlayerUrlSearch?searchTerm={}'.format(
player_name)
driver.get(match_url)
time.sleep(1)
html = driver.find_element_by_tag_name("pre").get_attribute('innerHTML')
json_obj = json.loads(html)
elements = json_obj["items"]
player_element = None
if len(elements) == 0:
import re
from datetime import datetime, date
import pandas as pd
import pickledb
from log import log, log_to_file, get_file_log
from queries.player_rank_queries import record_all_player_ranks, retrieve_all_player_ranks
from utils import get_chrome_driver
RANKS_LOGS = get_file_log("update_player_ranks")
def scrap_all_player_ranks(log_file_path, pickle_db_path):
driver = get_chrome_driver()
try:
driver.get("https://www.atptour.com/en/rankings/singles")
date_str = driver.find_element_by_xpath(
"//div[@class='dropdown-wrapper']/div[1]/div/div").text
last_ranking_date = datetime.strptime(date_str, '%Y.%m.%d').date()
today = date.today()
if last_ranking_date != today:
# Check if last ranking date on atptour match current date. If not, do not scrap
raise ValueError()
driver = get_chrome_driver(driver)
driver.get(
"https://www.atptour.com/en/rankings/singles?rankDate={0}&rankRange=1-5000"
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.ensemble import RandomForestClassifier
from joblib import dump, load
from log import log_to_file, get_file_log
from managers.match_manager import get_match_dtypes
from queries.match_queries import q_get_past_matches, q_update_match, get_embedded_matches_json, \
get_matches_collection, get_matches_from_created_date, q_get_unfeatured_matches, q_get_unpredicted_matches
from model_deployment.feature_engineering import get_categorical_cols, get_numerical_cols, add_features
PREDICT_LOGS = get_file_log("predict_matches")
def build_model():
# past_matches: all previous matches including when one player retired
past_matches = q_get_past_matches()
past_matches = past_matches.astype(get_match_dtypes(past_matches))
# finished_matches: matches that were played entirely
finished_matches = past_matches[past_matches["status"] ==
"Finished"].copy()
# matches = matches.replace({np.nan: None})
finished_matches = finished_matches[get_categorical_cols() +
get_numerical_cols() + ["p1_wins"]]
import time
import locale
import pandas as pd
import re
import configparser
from datetime import datetime, timedelta
from log import log, log_to_file, get_file_log
from queries.tournament_queries import find_tournament_by_id, q_update_tournament, q_create_tournament
from utils import get_chrome_driver, get_dataframe_json
config = configparser.ConfigParser()
config.read("config.ini")
TOURNAMENT_LOGS = get_file_log("tournament_updates")
def search_all_tournaments_atptour():
tournaments_atptour = None
driver = get_chrome_driver()
driver.get("https://www.atptour.com/en/tournaments")
time.sleep(3)
try:
atp_names = []
atp_formatted_names = []
atp_ids = []
elements = driver.find_elements_by_xpath(
"//tr[@class='tourney-result']/td[2]/a")
for elem in elements:
try:
url = elem.get_attribute("href")