betterdatascience

from flask import Flask, request, jsonify
from flask_sqlalchemy import SQLAlchemy
from flask_marshmallow import Marshmallow
from flask_restful import Resource, Api


app = Flask(__name__)
api = Api(app)
app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///users.db'
app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False

betterdatascience

# 1. Library imports
import pandas as pd 
from sklearn.ensemble import RandomForestClassifier
from pydantic import BaseModel
import joblib


# 2. Class which describes a single flower measurements
class IrisSpecies(BaseModel):
    sepal_length: float 

betterdatascience

from missingpy import MissForest

# Make an instance and perform the imputation
imputer = MissForest()
X = iris.drop('species', axis=1)
X_imputed = imputer.fit_transform(X)

betterdatascience

exp = explainer.explain_instance(
    data_row=X_test.iloc[4], 
    predict_fn=model.predict_proba
)

exp.show_in_notebook(show_table=True)

betterdatascience

name: str = 'Bob'
age: int = 32
rating: float = 7.9
is_premium: bool = True

betterdatascience

# Remap to integers
df['GENDER'] = [0 if x == 'M' else 1 for x in df['GENDER']]
df['CAR'] = [1 if x == 'Y' else 0 for x in df['CAR']]
df['REALITY'] = [1 if x == 'Y' else 0 for x in df['REALITY']]

# Create dummy variables
dummy_income_type = pd.get_dummies(df['INCOME_TYPE'], prefix='INC_TYPE', drop_first=True)
dummy_edu_type = pd.get_dummies(df['EDUCATION_TYPE'], prefix='EDU_TYPE', drop_first=True)
dummy_family_type = pd.get_dummies(df['FAMILY_TYPE'], prefix='FAM_TYPE', drop_first=True)
dummy_house_type = pd.get_dummies(df['HOUSE_TYPE'], prefix='HOUSE_TYPE', drop_first=True)

betterdatascience

ax = df['TARGET'].value_counts().plot(kind='bar', figsize=(10, 6), fontsize=13, color='#087E8B')
ax.set_title('Credit card fraud (0 = normal, 1 = fraud)', size=20, pad=30)
ax.set_ylabel('Number of transactions', fontsize=14)

for i in ax.patches:
    ax.text(i.get_x() + 0.19, i.get_height() + 700, str(round(i.get_height(), 2)), fontsize=15)

betterdatascience

from imblearn.over_sampling import SMOTE 

sm = SMOTE(random_state=42)

X_sm, y_sm = sm.fit_resample(X, y)

print(f'''Shape of X before SMOTE: {X.shape}
Shape of X after SMOTE: {X_sm.shape}''')

print('\nBalance of positive and negative classes (%):')

betterdatascience

lime_exp.as_list()

betterdatascience

shap.summary_plot(shap_values, X)