import numpy as np import matplotlib.pyplot as plt from pandas import DataFrame import pandas as pd import seaborn as sns

# Step 1 - create dataframe df=pd.read_csv('white_wine_quality.csv',sep=';') df.head(6)

# Step 1 continued. Is the wine acceptable? 1 = True, 0 = False df['acceptable'] = df.apply(lambda _: '', axis=1) df.loc[df.quality>= 7, "acceptable"] = 1 df.loc[df.quality<7, "acceptable"] = 0 df.head(15)

# Step 2. Nan values? df.isnull().values.any() #no NaN values print("This data set has",len(df.index), "instances")

# Step 3. Quality groupings and countplot df.sort_values(by=['quality']) for i in range (1,11): print ("Number of wines of quality ",i, " is ",len(df[df['quality'] == i]))

sns.countplot(df['quality']) #most wines have a quality o

# Step 4. For each feature determine if any data instance is an outlier; # if it is delete that data instance # Example follows for one feature

# doing features in given order f = df['fixed acidity'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in fixed acidity is ", count) f = df['volatile acidity'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in volatile acidity is ", count) f = df['citric acid'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in citric acid is ", count) f = df['residual sugar'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in residual sugar is ", count) f = df['chlorides'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in chlorides is ", count) f = df['free sulfur dioxide'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in free sulfur dioxide is ", count) f = df['total sulfur dioxide'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in total sulfur dioxide is ", count) f = df['density'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in density is ", count) f = df['pH'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in pH is ", count) f = df['sulphates'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in sulphates is ", count) f = df['alcohol'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in alcohol is ", count) f = df['quality'].values mean = np.mean(f) std = np.std(f) n = len(f) count = 0 for i in range (0,n): z = ( f[i] - mean ) if (z>5*std) : count = count + 1 df = df.drop( [i]) print ("number of data instances dropped due to outliers in quality is ", count) print("This data set has",len(df.index), "instances remaining")

# Step 5. get data into correct form # y = df.acceptable.values y=y.astype('int') # Get NumPy array for english and math scores, stack them and take transpose # Remember that np.vstack takes 1 argument so put your arrays in ( ) and remember to use .T to transpose f=df['fixed acidity'].values v=df['volatile acidity'].values c=df['citric acid'].values r=df['residual sugar'].values ch=df['chlorides'].values fr=df['free sulfur dioxide'].values t=df['total sulfur dioxide'].values d=df['density'].values p=df['pH'].values s=df['sulphates'].values a=df['alcohol'].values X = np.vstack((f,v,c,r,ch,fr,t,d,p,s,a)).T

# Step 6. Split data in test and trial sets with 80-20 split from sklearn.model_selection import train_test_split # # split the data (X_train,X_test, y_train, y_test )= \ train_test_split(X,y, test_size = 0.20, random_state=0) # # Print out length of each set n_train = len(X_train); n_test = len(X_test) print (n_train, n_test )

# Step 7. Scale the data from sklearn.preprocessing import StandardScaler scaler = StandardScaler() scaler.fit(X_train) X_train = scaler.transform(X_train) X_test = scaler.transform(X_test) scaler.fit(X ) X = scaler.transform(X )

# Step 8. Logistic Regression from sklearn.linear_model import LogisticRegression lr = LogisticRegression(solver ='lbfgs' ) # # Fit with training set lr.fit(X_train, y_train) # test_score = lr.score (X_test,y_test)*100 print ("The percent accuracy of logistic regression model on test set is ", \ round(test_score,2))

# Step 9. Create ANN classifier and train from sklearn.neural_network import MLPClassifier mlp = MLPClassifier ( max_iter = 300, solver='adam', random_state=1) mlp.fit(X_train,y_train) # # Print out precent accuracy of training set print ("Percent of accuracy of ANN on test data is ",100 * mlp.score (X_test,y_test) )

# Step 10. Create kNN classifier and see what value of k is best from sklearn.neighbors import KNeighborsClassifier for k in range (1,6): knn = KNeighborsClassifier (n_neighbors = k) knn.fit(X_train,y_train) # # Print out precent accuracy of training set print (f"Percent of accuracy on training data using k={k} is {100 * knn.score (X_train,y_train)}") #k=1 appears to be the best value for this situation knn = KNeighborsClassifier (n_neighbors = 1) knn.fit(X_train,y_train) # Print out percent accuracy of test set using kNN print ("Percent of accuracy on test data using kNN with k=1 is ",100 * knn.score(X_test,y_test) )

#using Naive Bayes algorithm from sklearn.naive_bayes import GaussianNB gnb = GaussianNB() y_pred = gnb.fit(X_train, y_train).predict(X_test) print ("Percent of accuracy using Naive Bayes on training data is ",100 * gnb.score (X_test,y_test) )

#using SVM algorithm from sklearn.svm import SVC svclassifier = SVC(kernel='linear') svclassifier.fit(X_train, y_train) y_pred = svclassifier.predict(X_test) print ("Percent of accuracy using SVM on training data is ",100 * svclassifier.score (X_test,y_test) )

#using decision tree algorithm from sklearn.tree import DecisionTreeClassifier classifier = DecisionTreeClassifier() classifier.fit(X_train, y_train) y_pred = classifier.predict(X_test) print ("Percent of accuracy using Decision Tree on training data is ",100 * classifier.score (X_test,y_test) )

# using the 3 required algorithms, logistic regression performed the worst only predicting around 80.4% correctly. # ANN was the middle of the bunch, clocking in at around 82.2% correct predictions. #K-means had optimal performance at k=1, and performed highest of the pack with 85.3% accurate prediction rates #I used Naive Bayes, SVM, and Decision tree algorithms as well. # The NB performed worse than the 3 required algorithms, being the lowest of all at 72.8% correct prediction. # SVM was slightly better than NB, but still worse than the required 3 at 77.6% correct prediction. #Decision tree actually performed better than all except k-means, with 82.9% accurate predictions.