socratesk

# import Flask class from the flask module
from flask import Flask, request

import numpy as np
import pickle

# Create Flask object to run
app = Flask(__name__)

@app.route('/')

socratesk

from sklearn.metrics import mean_squared_log_error
import numpy as np
rmsle = np.sqrt(mean_squared_log_error(y_actual, y_hat))

socratesk

from sklearn.metrics import mean_squared_error
import numpy as np
rmse = np.sqrt(mean_squared_error(y_actual, y_hat))

socratesk

from sklearn.metrics import mean_squared_error
mse = mean_squared_error(y_actual, y_hat)

socratesk

import pandas as pd

managerDF = pd.DataFrame({'id':[101, 102, 103, 104, 105, 106, 107, 108], 
                          'managerId':['D025', 'A010', 'C020', 'A010', 'D025', 'D025','A010', 'D025']})

managerDF['managerIdCount'] = managerDF['managerId'].map(managerDF.groupby('managerId').size())
managerDF.drop(['managerId'], axis=1, inplace=True)

print(managerDF)

socratesk

# Set number of splits
NO_SPLITS = fulldata.shape[0]

# Create KFold object with number of splits
kf = KFold(n_splits=NO_SPLITS)

socratesk

import pandas as pd

from sklearn import datasets
from sklearn.model_selection import KFold
from sklearn.linear_model import LogisticRegression

# Import breast cancer (dataset) object from sklearn library
breast_cancer = datasets.load_breast_cancer()

# Define features need to be extracted from breast cancer (dataset) object

socratesk

import pandas as pd

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

# Import breast cancer (dataset) object from sklearn library
breast_cancer = datasets.load_breast_cancer()

# Define features need to be extracted from breast cancer (dataset) object

socratesk

import pandas as pd

managerDF = pd.DataFrame({'id':[101, 102, 103, 104, 105, 106, 107, 108], 
                          'managerId':['D025', 'A010', 'C020', 'A010', 'D025', 'D025','A010', 'D025']})

# Group by category (managerId), compute sum of values in the category, sort by sum, and rank each value
idRank = managerDF.groupby('managerId').size().sort_values().rank().map(int)

# Map the ranks of items in the category to its respective item
managerDF['managerIdRank'] = managerDF['managerId'].map(idRank)

socratesk

import pandas as pd
from sklearn import preprocessing

countryDF = pd.DataFrame({'id' : [101, 102, 103], 
                          'country' : ['NZ', 'BR', 'US']})

labelEncode = preprocessing.LabelEncoder()
countryDF['countryLabel'] = labelEncode.fit_transform(countryDF['country']) 
countryDF.drop(['country'], axis=1, inplace=True)
print(countryDF)