def run(file_path):
obj = getData(file_path)
features, labels = obj.normalize_data()
features = features.as_matrix()
labels = labels.as_matrix()
features_train, features_test, labels_train, labels_test = train_test_split(features, labels)
clf = linear_model.LogisticRegression()
clf.fit(features_train, labels_train)
predection = clf.predict(features_test)
accuracy = accuracy_score(labels_test, predection)
print(accuracy)
def run(file_path):
obj = getData(file_path)
features, labels = obj.normalize_data()
features = features.as_matrix()
labels = labels.as_matrix()
features_train, features_test, labels_train, labels_test = train_test_split(
features, labels)
clf = tree.DecisionTreeClassifier(class_weight='balanced')
clf.fit(features_train, labels_train)
predection = clf.predict(features_test)
accuracy = accuracy_score(labels_test, predection)
print(accuracy)
def run(file_path):
obj = getData(file_path)
features, labels = obj.normalize_data()
# Convert DataFrames or Series into Numpy arrays
features = features.as_matrix()
labels = labels.as_matrix()
# Seperate train and test sets
features_train, features_test, labels_train, labels_test = train_test_split(features, labels)
# Train and predict
# clf = svm.SVC()
clf = GaussianNB()
clf.fit(features_train, labels_train)
prediction = clf.predict(features_test)
accuracy = accuracy_score(labels_test, prediction)
print(accuracy)
def __init__(self, file_path):
self.file_path = file_path
self.obj = getData(self.file_path)
#!/usr/bin/env python
import numpy as np
import pandas as pd
from sklearn import linear_model
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from normalize import getData
file_path = 'data/final_data.csv'
obj = getData(file_path)
features, labels = obj.normalize_data()
# Convert DataFrames or Series into Numpy arrays
features = features.as_matrix()
labels = labels.as_matrix()
# Seperate train and test sets
features_train, features_test, labels_train, labels_test = train_test_split(
features, labels)
# Train and predict
# clf = svm.SVC()
clf = linear_model.LinearRegression()
clf.fit(features_train, labels_train)
prediction = clf.predict(features_test)
accuracy = accuracy_score(labels_test, prediction)
#!/usr/bin/env python from normalize import getData training_file = 'data/main_data.csv' obj = getData(training_file) obj.plot_graphs()
