mprzybyla123

# what columns you want to group by
cols = ['Day', 'Ocean']

# picking the aggregation type ex: 'mean'
group = df_example.groupby(cols).agg({
 '1': ['mean'],
 '2: ['mean']})
  
# rename the column names with their respective aggregation type
group.columns = ["_".join(x) for x in group.columns.ravel()]

mprzybyla123

# import libraries
import pandas as pd
import numpy as np

# creating numeric data for columns "1" and "2"
df_example = pd.DataFrame(np.random.randint(0,100,size=(100, 2)), columns=list('12'))

# creating your categorical columns that will be grouping by
oceans = ['Pacific','Atlantic'] 
days = ['Monday', 'Tuesday', 'Wednesday']

mprzybyla123

data = {'text_field':  ['words word word12341****341234', '2132word word$$%3412', 'word 24234']}

df = pd.DataFrame (data, columns = ['text_field'])

import re

def cleaning_funciton(x):
    x = x.lower()
    x = re.sub('[^a-zA-Z\s]', '', x)
    return "".join(x)

mprzybyla123

# text and numeric classes that use sklearn base libaries
class TextTransformer(BaseEstimator, TransformerMixin):
    """
    Transform text features
    """
    def __init__(self, key):
        self.key = key
    def fit(self, X, y=None, *parg, **kwarg):
        return self
    def transform(self, X):

mprzybyla123

# text and numeric classes that use sklearn base libaries
class TextTransformer(BaseEstimator, TransformerMixin):
    """
    Transform text features
    """
    def __init__(self, key):
        self.key = key
def fit(self, X, y=None, *parg, **kwarg):
        return self
def transform(self, X):

mprzybyla123

# unite the features and classifier together
pipe = Pipeline([('features', features),
                 ('clf',clf)
                 ])
                 
# create grid 
param_grid = { 
    'n_estimators': [200, 300, 400],
    'max_features': ['auto', 'sqrt', 'log2'],
    'max_depth' : [4,6,8,10,20],

mprzybyla123

# common classifiers that can be optimized with parameter tuning
clf = RandomForestClassifier()
clf = MultinomialNB()
clf = LogisticRegression()
clf = svm.SVC()
clf = KNeighborsClassifier()

mprzybyla123

# import libraries
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn import svm

mprzybyla123

void setup(){
  size(500, 700);
  windmill1 = new Windmill(#E3D7CE, 100,265,1); 
  windmill2 = new Windmill(#E3D7CE, 250,265,.5);
  windmill3 = new Windmill(#E3D7CE, 400, 265, 1); 
  boat = new Boat (255, #5D4108, #483206, 0, 375, 1, 1);  
  background = new Background(255, 500, 1);
  water1 = new Water(#354164, 0, 5, 75);
  water2 = new Water(#394F90, 0, 1, 75);
  water3 = new Water(#445FAD, -25, 1, 75);

mprzybyla123

# import libraries
# sklearn reference: https://scikit-learn.org/0.19/about.html#citing-scikit-learn
# pandas reference: https://pandas.pydata.org/
from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score, StratifiedKFold
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline, FeatureUnion
import matplotlib.pyplot as plt