aSipiere

{
  "first names": {
    "Oliver": 4,
    "Kennedy": 4,
    "Adkins": 4,
    "Wyatt": 4,
    "Theodore": 4,
    "Nicholas": 4,
    "Alston": 3,
    "Donia": 3,

aSipiere

import pandas as pd
from pyproj import Transformer


def towgs84(row, lat_col, lon_col):
  """An apply function for a pyproj transformer from 4326/WGS84 to 3857/web mercator
  
  :param row: a row of a pandas dataframe as supplied by df.apply().
  :param lat_col: str of the lat col
  :param lon_col: str of the lon col

aSipiere

import geopandas as gpd
from shapely.ops import nearest_points 

def nearest(row, df1, df2, geom1_col='geometry', geom2_col='geometry', src_column=None):
    """Find the nearest point and return the corresponding value from specified column."""
    # Construct a multipoint object
    geom_union = df2.unary_union
    # Find the geometry that is closest
    nearest = df2[geom2_col] == nearest_points(row[geom1_col], geom_union)[1]
    # Get the corresponding value from df2 (matching is based on the geometry)

aSipiere

import os
import tempfile
import uuid
import argparse

import boto3
import azure.storage.blob as blob
import tqdm

aSipiere

import os
import csv
import argparse
from tqdm import tqdm

def split(filehandler, delimiter=',', row_limit=10000,
    output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    """
    Splits a CSV file into multiple pieces.

aSipiere

import foo
import argparse

def main(quux, quuz, **kwargs):
  try:
    if quux is True:
      foo.bar()
    else:
      foo.baz()
  except Exception as ex:

aSipiere

import boto3
import botocore
from joblib import Parallel, delayed
import os

bucket_name = "bucket_name"
s3 = boto3.resource('s3')
bucket = s3.Bucket(bucketname)
exists = True
try:

aSipiere

from collections import defaultdict

r_dd = lambda: defaultdict(r_dd)

aSipiere

reports = {}

for name, clf in zip(classifier_names, classifiers):
    clf.fit(X_train, Y_train)
    Y_predictions = clf.predict(X_test)
    Y_true = Y_test
    reports[name] = classification_report(Y_true, Y_predictions, output_dict=True)

reporting_df = pd.DataFrame.from_dict({(i,j): reports[i][j] 
                           for i in reports.keys() 

aSipiere

from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis