def run(self):
cl_qualifiers = cleanup_dataframe(
self.qualifiers_results(self.URL_CL_QUALIFIERS))
el_qualifiers = cleanup_dataframe(
self.qualifiers_results(self.URL_EL_QUALIFIERS))
cl_qualifiers = self.get_first_game_result(cl_qualifiers)
el_qualifiers = self.get_first_game_result(el_qualifiers)
save_output_to_csv(output=cl_qualifiers, filename="cl_qualifiers")
save_output_to_csv(output=el_qualifiers, filename="el_qualifiers")
def calculate_weight(df, my_uefa):
df_ranks = []
for year in my_uefa["Year"].unique():
df = my_uefa[my_uefa["Year"] == year]
df['Weight'] = [(x_i - min(df["Points"])) / (max(df["Points"]) - min(df["Points"])) for x_i in df["Points"]]
df_ranks.append(df)
return cleanup_dataframe(pd.concat(df_ranks))
def collect_uefa_clubs_ids(self):
ids = []
for season in range(self.SEASON_START, self.SEASON_END):
page_content = self.scrape_page(self._URL_UEFA_CLUBS_TABLE,
str(season))
ids.append(uefa_ids(page_content))
ids = pd.concat(ids).drop_duplicates()
return cleanup_dataframe(ids)
def collect_links_particular_seasons(self):
links_to_particular_seasons = []
similar_leagues_links = self.similar_leagues_results_links()
for row in similar_leagues_links.itertuples():
page_content = self.scrape_page(self.URL_SOCCERWAY_SEASON,
row.Link)
links_to_particular_seasons.append(
seasons_in_league(page_content, row.Country))
return cleanup_dataframe(pd.concat(links_to_particular_seasons))
def detailed_info_teams(self):
links = self.details_clubs_links()
detailed_top_tier_teams = []
for link in links:
page_content = self.scrape_page(self.URL_BASE, link)
detailed_top_tier_teams.append(
pd.DataFrame(self.collect_details(page_content,
link).to_dict(),
index=[0]))
return cleanup_dataframe(pd.concat(detailed_top_tier_teams))
def run_uefa_coeff(self):
uefa_rankings = []
for season_ranking in range(self.SEASON_START, self.SEASON_END + 1):
page_content = self.scrape_page(url=self._URL_UEFA,
suffix=str(season_ranking))
uefa_rankings.append(
uefa_country_rankings(page_content, season_ranking))
uefa_ranking_all_seasons = cleanup_dataframe(pd.concat(uefa_rankings))
uefa_ranking_similar_leagues = self.keep_similar_leagues(
uefa_ranking_all_seasons)
similar_leagues = pd.unique(uefa_ranking_similar_leagues["Country"])
return uefa_ranking_similar_leagues, similar_leagues
def run():
teams_full_record = cleanup_dataframe(read_input("teams_full_record"))
my_uefa = read_input("uefa_ranking")
weight = calculate_weight(teams_full_record, my_uefa)
teams_full_record = teams_full_record.merge(weight,
how="left",
left_on=["Country", "Year"],
right_on=["Country", "Year"])
calculate_score_for_single_cup(teams_full_record, "EL")
calculate_score_for_single_cup(teams_full_record, "CL")
calculate_score_for_single_cup(teams_full_record, "ELQ")
calculate_score_for_single_cup(teams_full_record, "CLQ")
calculate_score_for_single_cup(teams_full_record, "DL")
teams_full_record.replace(np.nan, 0, inplace=True)
calculate_score(teams_full_record)
save_output_to_csv(teams_full_record, "teams_score")
def check_empty(self, dfs):
if dfs:
return [cleanup_dataframe(pd.concat(dfs))]
else:
return []
def similar_leagues_results_links(self):
page_content = self.scrape_page(self.URL_SOCCERWAY)
all_leagues_links = cleanup_dataframe(
pd.concat([leagues_links_soccerway(page_content)]))
return all_leagues_links[all_leagues_links['Country'].isin(
self.similar_leagues())].reset_index(drop=True)