def load_api_result_csv(filename: str) -> DataFrame: csv_path = datasource.get_file_path(filename + ".csv") df = pd.read_csv(csv_path, header=0, names=[_ticketcount, _url, _duration], usecols=[_ticketcount, _url, _duration]) log.debug("Loaded data") log.debug(df) return df
def run_bulk_queries(inputfile="input-raw-calls.csv", outputfile="results-timed-api"): csv_path = datasource.get_file_path(inputfile) urls_to_call = pd.read_csv(csv_path, header=0, names=[_ticketcount, _url], usecols=[_ticketcount, _url]) results = [] for index, row in urls_to_call.iterrows(): ms = time_api(row, index) results.append(ms) log.info(f"{len(results)} results gathered") urls_to_call[_duration] = pd.Series(results) log.debug(urls_to_call) outputhelper.save_to_input_directory(urls_to_call, outputfile)
def foo(): csv_path = datasource.get_input_file_path() df = pd.read_csv(csv_path, header=1, names=["x", "y"], usecols=["x", "y"]) # print(df) # print(df.iloc[:, 0]) # print(df.iloc[:, 1]) df2 = pd.read_csv(datasource.get_file_path("additional.csv"), header=1, names=["a", "b", "c"], usecols=["b", "c"]) second_run = import_additional_results("input2", "csv") run_3 = import_additional_results_from_csv("input3") print(run_3) # print(df.join(df2)) # print(df.join(df2.iloc[:,0])) # df['b'] = df2.b df = df.join(second_run.input2) df = df.join(run_3.input3) fig = px.scatter(df, x=df.x, y=df.y) # fig.show() df_melt = df.melt(id_vars="x", value_vars=["y", "input2"]) print(df_melt) # fig = px.scatter(df, x=df_melt.x, y=df_melt.value, color=df_melt.variable) trace2 = go.Scatter(x=df.x, y=df.input2, mode="lines+markers") fig.add_trace(trace2) fig.show()
def import_additional_results(filename: str, extension: str) -> DataFrame: full_filename = filename + "." + extension csv_path = datasource.get_file_path(full_filename) df = pd.read_csv(csv_path, header=0, names=["x", filename], usecols=[0, 1]) return df
def raw_api_call_second(): df = pd.read_csv(datasource.get_file_path("raw-calls.csv")) df.duration = df.duration.apply(lambda x: probably_speed_up(x)) df.to_csv(datasource.get_file_path("raw-calls-2.csv"), index=False)