MaartenGr

from imblearn.over_sampling import SMOTE

# Different sampling strategies can be applied
X_resampled, y_resampled = SMOTE(sampling_strategy={"Fraud":1000}).fit_resample(X, y)

# 
X_resampled = pd.DataFrame(X_resampled, columns=X.columns)

MaartenGr

import pandas as pd
from imblearn.over_sampling import SMOTE

# Import data and create X, y
df = pd.read_csv('creditcard_small.csv')
X = df.iloc[:,:-1]
y = df.iloc[:,-1].map({1:'Fraud', 0:'No Fraud'})

# Resample data
X_resampled, y_resampled = SMOTE(sampling_strategy={"Fraud":1000}).fit_resample(X, y)

MaartenGr

import featuretools as ft
import pandas as pd

# Create Entity
turnover_df = pd.read_csv('turnover.csv')
es = ft.EntitySet(id = 'Turnover')
es.entity_from_dataframe(entity_id = 'hr', dataframe = turnover_df, index = 'index')

# Run deep feature synthesis with transformation primitives
feature_matrix, feature_defs = ft.dfs(entityset = es, target_entity = 'hr',

MaartenGr

# explicitly require this experimental feature
# now you can import normally from sklearn.impute
from sklearn.experimental import enable_iterative_imputer  
from sklearn.impute import IterativeImputer

from sklearn.ensemble import RandomForestRegressor
import pandas as pd

# Load data
titanic = pd.read_csv("titanic.csv")

MaartenGr

from sklearn.ensemble import IsolationForest
import pandas as pd
import seaborn as sns

# Predict and visualize outliers
credit_card = pd.read_csv('creditcard_small.csv').drop("Class", 1)
clf = IsolationForest(contamination=0.01, behaviour='new')
outliers = clf.fit_predict(credit_card)
sns.scatterplot(credit_card.V4, credit_card.V2, outliers, palette='Set1', legend=False)

MaartenGr

import pickle
import numpy as np
import pandas as pd
from lightgbm import LGBMClassifier
from sklearn.preprocessing import OneHotEncoder

# Load data and save indices of columns
df = pd.read_csv("data.csv")
features = df.drop('left', 1).columns
pickle.dump(features, open('features.pickle', 'wb'))

MaartenGr

# Data Handling
import pickle
import numpy as np
from pydantic import BaseModel

# Server
import uvicorn
from fastapi import FastAPI

# Modeling

MaartenGr

import requests
to_predict_dict = {'satisfaction_level': 0.38,
                   'last_evaluation': 0.53,
                   'number_project': 2,
                   'average_montly_hours': 157,
                   'time_spend_company': 3,
                   'Work_accident': 0,
                   'promotion_last_5years': 0,
                   'sales': 'support',
                   'salary': 'low'}

MaartenGr

FROM tiangolo/uvicorn-gunicorn:python3.6-alpine3.8

# Make directories suited to your application
RUN mkdir -p /home/project/app
WORKDIR /home/project/app

# Copy and install requirements
COPY requirements.txt /home/project/app
RUN pip install --no-cache-dir -r requirements.txt

MaartenGr

import numpy as np
from sklearn.model_selection import train_test_split
X, y = np.arange(10).reshape((5, 2)), range(5)
(X_train, X_test, 
 y_train, y_test) = train_test_split(X, y, test_size=0.3, 
                                     random_state=42)