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

@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)

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

        funclist = []

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

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

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

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

from sklearn.inspection import permutation_importance

# Here's how you use permutation importance
def get_permutation_importance(X, y, model) -> pd.DataFrame:
    result = permutation_importance(model, X, y, n_repeats=1,
                                random_state=0)
    
    # permutational importance results
    result_df = pd.DataFrame(colnames,  columns=['Feature'])
    result_df['permutation_importance'] = result.get('importances')

gvyshnya

from sklearn.feature_selection import SelectFromModel

embeded_rf_selector = SelectFromModel(modeller, max_features=200)
embeded_rf_selector.fit(X, y)

embeded_rf_support = embeded_rf_selector.get_support()
embeded_rf_feature = X.loc[:,embeded_rf_support].columns.tolist()

gvyshnya

from sklearn.feature_selection import RFE

# Define dictionary to store our rankings
ranks = {}
# Create our function which stores the feature rankings to the ranks dictionary
def ranking(ranks, names, order=1):
    minmax = MinMaxScaler()
    ranks = minmax.fit_transform(order*np.array([ranks]).T).T[0]
    ranks = map(lambda x: round(x,2), ranks)
    return dict(zip(names, ranks))