gvyshnya

from sklearn.base import clone 

def drop_col_feat_imp(model, X_train, y_train, random_state = 42):
    
    # clone the model to have the exact same specification as the one initially trained
    model_clone = clone(model)
    # set random_state for comparability
    model_clone.random_state = random_state
    # training and scoring the benchmark model
    model_clone.fit(X_train, y_train)

gvyshnya

import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
import matplotlib.pyplot as plt

# Missing value summary
nan_columns = []
nan_values = []

for column in df.columns:

gvyshnya

import datetime
from pyspark.sql.functions import year, month, dayofmonth

elevDF = sc.parallelize([
    (datetime.datetime(1994, 1, 1, 0, 0), 1, 638.55),
    (datetime.datetime(1994, 1, 1, 0, 0), 2, 638.55),
    (datetime.datetime(1994, 1, 1, 0, 0), 3, 638.55),
    (datetime.datetime(1994, 1, 1, 0, 0), 4, 638.55),
    (datetime.datetime(1994, 1, 1, 0, 0), 5, 638.55)
]).toDF(["date", "hour", "value"])

gvyshnya

def extract_feature_means(audio_file_path: str) -> pd.DataFrame:
    # config settings
    number_of_mfcc = c.NUMBER_OF_MFCC

    # 1. Importing 1 file
    y, sr = librosa.load(audio_file_path)

    # Trim leading and trailing silence from an audio signal (silence before and after the actual audio)
    signal, _ = librosa.effects.trim(y)

gvyshnya

    for ebird in final_data:
        print("Starting to process a new species: ", ebird)
        ebird_data = train_csv[train_csv['species'] == ebird]

        short_file_name = ebird_data['ebird_code'].unique()[0]
        print("Short file name: ", short_file_name)

        pool = mp.Pool(c.NUMBER_OF_CPU_IN_POOL)  # use the number of parallel processes as per the configured

        funclist = []

gvyshnya

@ray.remote
def extract_feautres(trial_audio_file_path):
    # process data frame
    function_start_time = dt.datetime.now()
    print("Started a file processing at ", function_start_time)

    df0 = u.extract_feature_means(trial_audio_file_path)

    function_finish_time = dt.datetime.now()
    print("Fininished the file processing at ", function_finish_time)

gvyshnya

    for ebird in final_data:
        print("Starting to process a new species: ", ebird)
        ebird_data = train_csv[train_csv['species'] == ebird]

        short_file_name = ebird_data['ebird_code'].unique()[0]
        print("Short file name: ", short_file_name)

        result = []

        for index, row in ebird_data.iterrows():

gvyshnya

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import datetime as dt
from typing import Tuple

import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.express as px

gvyshnya

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import datetime as dt
from typing import Tuple

import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.express as px

gvyshnya

def visualize_features_vs_target_label(df_data, label, feature_list, n_cols=3):
    
    if len(feature_list) % n_cols == 0:
    
        number_of_rows = int(len(feature_list)/n_cols)
    else:
        number_of_rows = int(len(feature_list)/n_cols) +1
    
    fig = make_subplots(rows=number_of_rows, cols=n_cols)