modelGenerator.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import sklearn
from sklearn.externals import joblib

def simplify_ages(df):
    df.Age = df.Age.fillna(-0.5)
    bins = (-1, 0, 5, 12, 18, 25, 35, 60, 120)
    group_names = ['Unknown', 'Baby', 'Child', 'Teenager', 'Student', 'Young Adult', 'Adult', 'Senior']
    categories = pd.cut(df.Age, bins, labels=group_names)
    df.Age = categories
    return df


def transform_features(df):
    df = simplify_ages(df)
    return df


#Normalize#########################################################
from sklearn import preprocessing

def encode_features(df_train):
    features = ['Age']
   
    for feature in features:
        le = preprocessing.LabelEncoder()
        le = le.fit(df_train[feature])
        df_train[feature] = le.transform(df_train[feature])
    return df_train
 

def to_str(var):
    return str(list(np.reshape(np.asarray(var), (1, np.size(var)))[0]))[1:-1]


#Train################################################################
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import make_scorer, accuracy_score
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split


sklearnv = 'sklearn version = ' + sklearn.__version__
print(sklearnv)

data_train = pd.read_csv('./csv_training_data/Final_TrainingSet.csv')
data_train = transform_features(data_train)
data_train = encode_features(data_train)

X_all = data_train.drop(['Disease'], axis=1)
y_all = data_train['Disease']

num_test = 0.20
X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=num_test, random_state=23)


# Choose the type of classifier. 
clf = RandomForestClassifier()

# Choose some parameter combinations to try
parameters = {'n_estimators': [4, 6, 9], 
              'max_features': ['log2', 'sqrt','auto'], 
              'criterion': ['entropy', 'gini'],
              'max_depth': [2, 3, 5, 10], 
              'min_samples_split': [2, 3, 5],
              'min_samples_leaf': [1,5,8]
             }

# Type of scoring used to compare parameter combinations
acc_scorer = make_scorer(accuracy_score)

# Run the grid search
grid_obj = GridSearchCV(clf, parameters, scoring=acc_scorer)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
clf = grid_obj.best_estimator_

# Fit the best algorithm to the data. 
clf.fit(X_train, y_train)

predictions = clf.predict(X_test)
print("ACCURACY = ", accuracy_score(y_test, predictions))

# save the model to disk
filename = 'eye_finalized_model.sav'
joblib.dump(clf, filename)