Predicción de la calidad del vino: aprendizaje automático

Aquí predeciremos la calidad del vino sobre la base de las características dadas. Utilizamos el conjunto de datos de calidad del vino de Kaggle. Este conjunto de datos tiene las características fundamentales que son responsables de afectar la calidad del vino. Mediante el uso de varios modelos de Machine learning, predeciremos la calidad del vino. Aquí solo nos ocuparemos de la calidad del vino de tipo blanco, utilizamos técnicas de clasificación para verificar más a fondo la calidad del vino, es decir, si es bueno o lecho. 

Conjunto de datos : aquí

# import libraries
 
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sb

# loading the data
Dataframe = pd.read_csv(R'D:\\xdatasets\winequalityN.csv')

# show rows and columns
Dataframe.head()

# getting info.
Dataframe.info()

Dataframe.describe()

# null value check
Dataframe.isnull().sum()

# plot pairplot
sb.pairplot(Dataframe)
#show graph
plt.show()

#plot histogram
Dataframe.hist(bins=20,figsize=(10,10))
#plot showing
plt.show()

plt.figure(figsize=[15,6])
plt.bar(df['quality'],df['alcohol'])
plt.xlabel('quality')
plt.ylabel('alcohol')
plt.show()

# correlation by visualization
plt.figure(figsize=[18,7])
# plot correlation
sb.heatmap(Dataframe.corr(),annot=True)
plt.show()

colm = []
# loop for columns
for i in range(len(Dataframe.corr().keys())):
# loop for rows
  for j in range(j):
    if abs(Dataframe.corr().iloc[i,j]) > 0.7:
      colm = Dataframe.corr().columns[i]

# drop column
new_df = Dataframe.drop('total sulfur dioxide',axis = 1)

new_df.update(new_df.fillna(new_df.mean()))

# no of categorical columns
cat = new_df.select_dtypes(include='O')
# create dummies of categorical columns
df_dummies = pd.get_dummies(new_df,drop_first = True)
print(df_dummies)

df_dummies['best quality']=[1 if x>=7 else 0 for x in Dataframe.quality]
print(df_dummies)

# import libraries
from sklearn.preprocessing import train_test_split
 
# independent variables
x = df_dummies.drop(['quality','best quality'],axis=1)
# dependent variable
y = df_dummies['best quality']
 
# creating train test splits
xtrain,xtest,ytrain,ytest = train_test_split(x,y,test_size=0.2,random_state=40)

# code
# import libraries
 
from sklearn.preprocessing import MinMaxScaler
# creating scaler scale var.
norm = MinMaxScaler()
# fit the scale
norm_fit = norm.fit(xtrain)
# transformation of training data
scal_xtrain = norm_fit.transform(xtrain)
# transformation of testing data
scal_xtest = norm_fit.transform(xtest)
print(scal_xtrain)

# code
#import libraries
from sklearn.ensemble import RandomForestClassifier
 
# for error checking
from sklearn.metrics import mean_squared_error
 
from sklearn.metrics import classification_report
 
# create model variable
rnd = RandomForestClassifier()
 
# fit the model
fit_rnd = rnd.fit(new_xtrain,ytrain)
 
# checking the accuracy score
rnd_score = rnd.score(new_xtest,ytest)
 
print('score of model is : ',rnd_score)
 
print('.................................')
 
print('calculating the error')
 
# checking mean_squared error
MSE = mean_squared_error(ytest,y_predict)
 
# checking root mean squared error
RMSE = np.sqrt(MSE)
 
print('mean squared error is : ',MSE)
 
print('root mean squared error is : ',RMSE)
 
print(classification_report(ytest,x_predict))

# code
x_predict = list(rnd.predict(xtest))
df = {'predicted':x_predict,'original':ytest}
pd.DataFrame(df).head(10)