
import yaml
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


df = pd.read_csv('WineQT.csv')


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1143 entries, 0 to 1142
Data columns (total 13 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   fixed acidity         1143 non-null   float64
 1   volatile acidity      1143 non-null   float64
 2   citric acid           1143 non-null   float64
 3   residual sugar        1143 non-null   float64
 4   chlorides             1143 non-null   float64
 5   free sulfur dioxide   1143 non-null   float64
 6   total sulfur dioxide  1143 non-null   float64
 7   density               1143 non-null   float64
 8   pH                    1143 non-null   float64
 9   sulphates             1143 non-null   float64
 10  alcohol               1143 non-null   float64
 11  quality               1143 non-null   int64  
 12  Id                    1143 non-null   int64  
dtypes: float64(11), int64(2)
memory usage: 116.2 KB


df.describe()


df.head(10)


df.isna().sum() # checking for null values

fixed acidity           0
volatile acidity        0
citric acid             0
residual sugar          0
chlorides               0
free sulfur dioxide     0
total sulfur dioxide    0
density                 0
pH                      0
sulphates               0
alcohol                 0
quality                 0
Id                      0
dtype: int64


df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality', 'Id'],
      dtype='object')


df = df.drop('Id',axis=1)


df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')


plt.figure(figsize=(12,12))
sns.heatmap(df.corr(),annot=True,cmap='coolwarm',linecolor='white',linewidths=1) # complete correlation of all variables
#sns.heatmap(df.corr()[df.corr()>0.6],annot=True,cmap='coolwarm',linecolor='white',linewidths=1) # correlations with > 0.6

<AxesSubplot: >


sns.countplot(data = df, x = 'quality')

<AxesSubplot: xlabel='quality', ylabel='count'>


sns.boxplot(data = df, y= 'fixed acidity', x = 'quality')

<AxesSubplot: xlabel='quality', ylabel='fixed acidity'>


sns.pairplot(data=df,corner=True)

<seaborn.axisgrid.PairGrid at 0x296c3112430>


g=sns.FacetGrid(data=df,col='quality')
g.map(plt.hist,'fixed acidity')

<seaborn.axisgrid.FacetGrid at 0x296c677f460>


sns.kdeplot(x='citric acid',y='quality',data=df)

<AxesSubplot: xlabel='citric acid', ylabel='quality'>


df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')


for i in df.columns:
    plt.figure()
    sns.histplot(df[i],kde=True)


from sklearn import preprocessing


X = df.drop('quality',axis=1)
y = df['quality']


scaler = preprocessing.StandardScaler()


xdf = scaler.fit_transform(X)
xdf = pd.DataFrame(xdf,columns=X.columns)
xdf


X = xdf
y = df['quality']


from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from sklearn.metrics import explained_variance_score
from sklearn.metrics import r2_score


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)


lr = LinearRegression()
lr.fit(X_train,y_train)

test_predictions = lr.predict(X_test)
train_predictions = lr.predict(X_train)


test_r2 = r2_score(y_test,test_predictions)
train_r2 = r2_score(y_train,train_predictions)
MAE = metrics.mean_absolute_error(y_test, test_predictions)
MSE = metrics.mean_squared_error(y_test, test_predictions)
RMSE = np.sqrt(metrics.mean_squared_error(y_test, test_predictions))

print('Test R2: ',test_r2)
print('Train R2: ',train_r2)
print('MAE: ', MAE)
print('MSE: ', MSE)
print('RMSE: ', RMSE)

Test R2:  0.3368152773954599
Train R2:  0.3827250369452767
MAE:  0.4801747424866615
MSE:  0.3855917837384165
RMSE:  0.6209603721159801


plt.scatter(y_test,test_predictions)

<matplotlib.collections.PathCollection at 0x2969efcbd30>


from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score, KFold, RepeatedStratifiedKFold
from sklearn.metrics import confusion_matrix,classification_report,accuracy_score, ConfusionMatrixDisplay
from sklearn.model_selection import GridSearchCV


model = RandomForestClassifier(n_estimators=200,max_depth=15)
parameters = {'n_estimators' : [100,150,200],
             'max_depth' : [5,10,15]}

grid_RFC = GridSearchCV(estimator = model, param_grid = parameters, cv = 5, n_jobs = -1, verbose=1,return_train_score = True)
grid_RFC.fit(X_train,y_train)

print(grid_RFC.best_estimator_)
print(grid_RFC.best_score_)

grid_RFC_test_predictions = grid_RFC.predict(X_test)
grid_RFC_train_predictions = grid_RFC.predict(X_train)

Fitting 5 folds for each of 9 candidates, totalling 45 fits
RandomForestClassifier(max_depth=15)
0.6525


CM=confusion_matrix(y_test,grid_RFC_test_predictions,labels=grid_RFC.classes_)
disp = ConfusionMatrixDisplay(confusion_matrix=CM, display_labels=grid_RFC.classes_)
disp.plot(cmap='viridis')
plt.grid(None)


print(classification_report(y_test,grid_RFC_test_predictions))
#print(classification_report(y_pred,y_valid))

              precision    recall  f1-score   support

           4       0.00      0.00      0.00         9
           5       0.67      0.74      0.70       143
           6       0.64      0.64      0.64       146
           7       0.65      0.59      0.62        41
           8       1.00      0.25      0.40         4

    accuracy                           0.65       343
   macro avg       0.59      0.44      0.47       343
weighted avg       0.64      0.65      0.64       343

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	Id
count	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000	1143.000000
mean	8.311111	0.531339	0.268364	2.532152	0.086933	15.615486	45.914698	0.996730	3.311015	0.657708	10.442111	5.657043	804.969379
std	1.747595	0.179633	0.196686	1.355917	0.047267	10.250486	32.782130	0.001925	0.156664	0.170399	1.082196	0.805824	463.997116
min	4.600000	0.120000	0.000000	0.900000	0.012000	1.000000	6.000000	0.990070	2.740000	0.330000	8.400000	3.000000	0.000000
25%	7.100000	0.392500	0.090000	1.900000	0.070000	7.000000	21.000000	0.995570	3.205000	0.550000	9.500000	5.000000	411.000000
50%	7.900000	0.520000	0.250000	2.200000	0.079000	13.000000	37.000000	0.996680	3.310000	0.620000	10.200000	6.000000	794.000000
75%	9.100000	0.640000	0.420000	2.600000	0.090000	21.000000	61.000000	0.997845	3.400000	0.730000	11.100000	6.000000	1209.500000
max	15.900000	1.580000	1.000000	15.500000	0.611000	68.000000	289.000000	1.003690	4.010000	2.000000	14.900000	8.000000	1597.000000

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	Id
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	0
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5	1
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5	2
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6	3
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	4
5	7.4	0.66	0.00	1.8	0.075	13.0	40.0	0.9978	3.51	0.56	9.4	5	5
6	7.9	0.60	0.06	1.6	0.069	15.0	59.0	0.9964	3.30	0.46	9.4	5	6
7	7.3	0.65	0.00	1.2	0.065	15.0	21.0	0.9946	3.39	0.47	10.0	7	7
8	7.8	0.58	0.02	2.0	0.073	9.0	18.0	0.9968	3.36	0.57	9.5	7	8
9	6.7	0.58	0.08	1.8	0.097	15.0	65.0	0.9959	3.28	0.54	9.2	5	10

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol
0	-0.521580	0.939332	-1.365027	-0.466421	-0.231395	-0.450467	-0.363610	0.555854	1.270695	-0.573658	-0.963382
1	-0.292593	1.941813	-1.365027	0.050060	0.234247	0.915920	0.643477	0.036165	-0.708928	0.130881	-0.593601
2	-0.292593	1.273492	-1.161568	-0.171289	0.107253	-0.060071	0.246745	0.140103	-0.325775	-0.045254	-0.593601
3	1.653789	-1.399789	1.483400	-0.466421	-0.252560	0.135127	0.429852	0.659792	-0.964363	-0.456235	-0.593601
4	-0.521580	0.939332	-1.365027	-0.466421	-0.231395	-0.450467	-0.363610	0.555854	1.270695	-0.573658	-0.963382
...	...	...	...	...	...	...	...	...	...	...	...
1138	-1.151292	-0.118842	-0.703785	-0.171289	-0.231395	1.306316	-0.180503	-0.514707	0.695966	0.541862	0.515741
1139	-0.865059	0.493785	-0.958109	-0.466421	-0.400719	1.208717	-0.241539	-0.114545	0.695966	0.952843	-0.870937
1140	-1.208538	0.382399	-0.958109	-0.392638	0.064922	1.599113	-0.058432	-0.951246	0.887542	-0.456235	0.053515
1141	-1.380278	0.103932	-0.856379	-0.245072	-0.527712	2.282306	0.155192	-0.836914	1.334554	0.600574	0.700632
1142	-1.380278	0.633019	-0.754650	-0.392638	-0.252560	1.599113	-0.058432	-0.655023	1.653848	0.307016	-0.223820

Wine quality prediction

LR model

Random forest classifier