import sys sys.path.insert(0, '/home/freddie/git/DataScience/dataPreProcess/') from data_process import DataPreparation from sklearn.tree import DecisionTreeClassifier from sklearn.metrics import confusion_matrix import statsmodels.formula.api as sm import numpy from sklearn.preprocessing import Imputer, LabelEncoder, OneHotEncoder, StandardScaler import matplotlib.pyplot as plot from matplotlib.colors import ListedColormap data_file="""/home/freddie/git/DataScience/data/Machine Learning A-Z \ Template Folder/Part 3 - Classification/Section 14 -\ Logistic Regression/Social_Network_Ads.csv""" prep = DataPreparation(data_file) indep_vars, dep_vars, data_frame = prep.prepare_data_frame([2,4], [4,5]) indep_vars = prep.feature_scaling(indep_vars, None) sc_indep = StandardScaler() indep_train, indep_test, dep_train, dep_test = prep.partition_training_test() scale_X_train = sc_indep.fit_transform(indep_train) scale_X_test = sc_indep.transform(indep_test) classifier = DecisionTreeClassifier(criterion = 'entropy') classifier.fit(scale_X_train, dep_train[:,-1]) y_pred = classifier.predict(indep_test) cm = confusion_matrix(dep_test, y_pred) #plot
""" Created on Wed Jan 3 20:02:07 2018 @author: freddie """ import sys sys.path.insert(0, '/home/freddie/git/DataScience/dataPreProcess/') from data_process import DataPreparation from sklearn.linear_model import LinearRegression from sklearn.tree import DecisionTreeRegressor import statsmodels.formula.api as sm import numpy import matplotlib.pyplot as plot data_file = """/home/freddie/git/DataScience/data/\ Machine Learning A-Z Template Folder/Part 2 -\ Regression/Section 8 - Decision Tree Regression/Position_Salaries.csv""" prep = DataPreparation(data_file) indep_vars, dep_vars, data_frame = prep.prepare_data_frame([1, 2], [2, 3]) regressor = DecisionTreeRegressor(random_state=0) regressor.fit(indep_vars, dep_vars) y_pred = regressor.predict(6.5) indep_grid = numpy.arange(min(indep_vars), max(indep_vars), 0.1) indep_grid = indep_grid.reshape((len(indep_grid), 1)) plot.plot(indep_grid, regressor.predict(indep_grid), color='blue') plot.scatter(indep_vars, dep_vars, color='red')
import sys
sys.path.insert(0, '/home/freddie/git/DataScience/dataPreProcess/')
from data_process import DataPreparation
import scipy.cluster.hierarchy as hierarchy
from sklearn.cluster import AgglomerativeClustering
import matplotlib.pyplot as plot
import pandas
from apyori import apriori
data_file = """/home/freddie/git/DataScience/data/Machine Learning A-Z Template Folder/Part 5 - Association Rule Learning/Section 28 - Apriori/Market_Basket_Optimisation.csv"""
prep = DataPreparation(data_file)
data_frame = pandas.read_csv(data_file, header=None)
transactions = []
for i in range(0, 7501):
transactions.append([str(data_frame.values[i, j]) for j in range(0, 20)])
rules = apriori(transactions,
min_support=0.003,
min_confidence=0.2,
min_lift=3,
min_length=2)
results = list(rules)
# -*- coding: utf-8 -*-
import sys
sys.path.insert(0, '/home/freddie/git/DataScience/dataPreProcess/')
from data_process import DataPreparation
import scipy.cluster.hierarchy as hierarchy
from sklearn.cluster import AgglomerativeClustering
import matplotlib.pyplot as plot
data_file = """/home/freddie/git/DataScience/data/Machine Learning A-Z Template Folder/Part 4 - Clustering/Section 24 - K-Means Clustering/Mall_Customers.csv"""
prep = DataPreparation(data_file)
indep_vars, dep_vars, data_frame = prep.prepare_data_frame([2, 4], [4, 5])
X = data_frame.iloc[:, [3, 4]].values
dendrogram = hierarchy.dendrogram(hierarchy.linkage(X, method='ward'))
hc = AgglomerativeClustering(n_clusters=5,
affinity='euclidean',
linkage='ward')
y_hc = hc.fit_predict(X)
#visualise
plot.scatter(X[y_hc == 0, 0], X[y_hc == 0, 1], s=100, c='red', label='Schnoep')
plot.scatter(X[y_hc == 1, 0],
X[y_hc == 1, 1],
s=100,
c='blue',
label='moderate')
plot.scatter(X[y_hc == 2, 0],
X[y_hc == 2, 1],
s=100,
#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Wed Dec 27 11:39:32 2017 @author: freddie """ import sys sys.path.insert(0, '/home/freddie/git/DataScience/dataPreProcess/') from data_process import DataPreparation from sklearn.linear_model import LinearRegression import statsmodels.formula.api as sm import numpy data_file = """/home/freddie/git/DataScience/data/Machine Learning A-Z Template Folder/Part 2 - Regression/Section 5 - Multiple Linear Regression/50_Startups.csv""" prep = DataPreparation(data_file) indep_vars, dep_vars, data_frame = prep.prepare_data_frame([0,4], [4,5]) #here one of the dummy variables need to be removed to avoid the Dummy variable trap. #This is automatically done with the current libs but we will remove a dummy variable anyway. indep_vars, dep_vars = prep.add_dummy_variables(encode_dep=False, columns=[3]) indep_vars = indep_vars[:,1:] indep_train, indep_test, dep_train, dep_test = prep.partition_training_test() #no need to scale feature. lr lib does that or us. regressor = LinearRegression() regressor.fit(indep_train, dep_train) dep_pred = regressor.predict(indep_test) error = dep_pred-dep_test