GabrielSGoncalves

GabrielSGoncalves

GabrielSGoncalves

import papermill as pm

pm.execute_notebook('weather_forecast_using_pyowm.ipynb',
                    'weather_forecast_using_pyowm_output.ipynb',
                    parameters={'city':'Sao Paulo,BR'},
                    kernel_name='papermill-tutorial')

GabrielSGoncalves

import json
import os
import boto3

def load_file_from_S3(key, bucket):
    """Download file from S3 to /tmp/ folder"""
    local_path = key.split('/')[-1]
    print(key)
    print(local_path)
    filename = f'/tmp/{local_path}'

GabrielSGoncalves

def parsing_lambda_logs(RequestId, GroupName , StreamName):
    """
    Function that parses Lambda Logs on CloudWatch using boto3
    
    Parameters:
    ===========
    RequestId (str): Unique identifier for each AWS Lambda call
    GroupName (str): Name of the Lambda Function group on CloudWatch
    StreamName (str): Name of the log stream for the Function container

GabrielSGoncalves

import cPickle
import bz2


def save(filename, myobj):
    """
    save object to file using pickle
    
    @param filename: name of destination file
    @type filename: str

GabrielSGoncalves

import plotly.graph_objects as go
from plotly.subplots import make_subplots

fig = make_subplots(rows=2, cols=1,)

fig.add_trace(
    go.Scatter(
        x=df_analysis.index,
        y=df_analysis.fpd_by_amount,
        mode="lines+markers+text",

GabrielSGoncalves

import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.express as px

import plotly.graph_objects as 
fig = make_subplots(rows=1, cols=2)
colors = px.colors.qualitative.Set1
text_position = [
    "top center",
    "bottom center",

GabrielSGoncalves

import pandas as pd
from optbinning import Scorecard, BinningProcess
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

# Load the train dataset
df_application = pd.read_csv('./home-credit-default-risk/application_train.csv', low_memory=True)
df_application.set_index('SK_ID_CURR', inplace=True)

# Split the dataset into train and test

GabrielSGoncalves

# Define the feature list from dataset (including categorical and numerical)
list_features = df_application_train.drop(columns=['TARGET']).columns.values

# Define categorical features list
list_categorical = df_application_train.select_dtypes(include=['object', 'category']).columns.values

# Define selection criteria for BinningProcess
selection_criteria = {"iv": {"min": 0.005, 'max':0.5, "strategy": "highest"}}

# Instatiate BinningProcess