socratesk

import pandas as pd
import numpy as np

platformDF = pd.DataFrame({'id' : [101, 102, 103, 104, 105, 106], 
                           'platform' : ['Android', 'Android', 'iOS', np.nan, 'Android', 'iOS']})

platformDF.platform = platformDF.platform.fillna('NaN')
onehotDF = pd.get_dummies(platformDF)
print(onehotDF)

socratesk

import pandas as pd
from sklearn import preprocessing

vehiclerDF = pd.DataFrame({'id':[101, 102, 103, 104, 105, 106, 107, 108], 
                          'vehicle':['Car', 'Minivan', 'SUV', 'Car', 'Car', 'Minivan','Car', 'Minivan'],
                          'label':['Yes', 'Yes', 'Yes', 'No', 'Yes', 'No','Yes', 'No']})

# Encode label (target)
labelEncode = preprocessing.LabelEncoder()
vehiclerDF['label'] = labelEncode.fit_transform(vehiclerDF['label']) 

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

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)

socratesk

import pandas as pd

country = ['NZ', 'BR', 'US']
onehotDF = pd.get_dummies(country)
print(onehotDF)

socratesk

# import libraries
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor

# load data file
train = pd.read_csv('50-Startups.csv')

# perform one-hot encoding for categorical variable
trainDummies = pd.get_dummies(train['State'], prefix = 'state')

socratesk

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

import numpy as np
import pickle

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

@app.route('/')

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

# This is a sample model to demonstrate how a Machine Learning model 
# can be implemented in Production as a REST API and how it can be consumed

# Import libraries and packages
from sklearn import svm, datasets
import pickle 
import numpy as np

# Load Sample data
iris = datasets.load_iris()