Wine quality project

#1

I got the accuracy as 83% by using random forest .How can i increase it more?
I have used cross validation and standardscaler()
Below are the best parameter i got using grid search
RandomForestRegressor(bootstrap=True, criterion=‘mse’, max_depth=None,
max_features=2, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=30,
n_jobs=None, oob_score=False, random_state=42, verbose=0,
warm_start=False)

#2

Hi Shivom,

You can try a different model, like XGBoost.

Thanks.

#3

In Wine Quality Project, I am trying alternative methods of importing a dataset.
Incase if you are taking the code from sklearn library, —

from sklearn import datasets

wine_data = datasets.load_wine()
wine_data
By doing so----the output is in the form of a Dictionary.

To see the aforesaid Dictionary output in a formatted structure —

print(wine_data[‘DESCR’])

Upon executing this, getting the following output which is being shared as a screenshot.

Doubts/Queries are as follows—
Q1 is what are class_0, class_1 & class_2 in this dataset? I didn’t understand this part…

Capture-Wine Dataset_1
Capture-Wine Dataset_11082×608 58.2 KB

Q2 Since the original data-set is in the form of a Dictionary, is it possible to convert the same into a Pandas dataframe? How do I do the conversion???

Is there any reference material on this topic/subject for understanding this aspect better?

Q3 Again one more interesting aspect is noticed…

  1. Upon importing as Dataframe, 12 variables can be noticed under Descriptive Statistics,

  2. Upon importing as a Dictionary, 13 variables are noticed under Descriptive Statistics…

D280/OD315 of diluted wines is variable is missing while importing the raw data as a Dataframe, but can be seen while being imported as a Dictionary data-structure??? Why is this so???

Can someone explain???

#4

Hi Sameer,

You can find more about the dataset from the below link:

https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_wine.html

If there is a target, and data component in the dictionary, you can use the following:

iris = load_wine()
X = wine.data
y = wine.target

Without looking at your code, it would be impossible to comment on your third question. Also, I would suggest you to start a new thread since the original topic for this thread is different from your queries.

Thanks.

1 Like
#5

Hi Rajtilak,

Sorry for the delay in replying to & acknowledging your message.

Appreciate for sharing the link

I have noted your comments and shall start a new thread for the topic.

Thanks once again.