music1.txt

import pandas as pd
from sklearn.tree import DecisionTreeClassifier

music_data = pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']

model = DecisionTreeClassifier()
model.fit(X, y)

predictions = model.predict([ [21, 1], [22, 0] ])

music2.txt

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

music_data = pd.read_csv('music.csv')  # this returns a data frame similar to an excel spreadsheet
X = music_data.drop(columns=['genre'])
y = music_data['genre']  # using `[]` we can get all the values in a given column

# we are allocating 20% of our data for testing. this returns a tuple
# we will unpack the tuple
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)


model = DecisionTreeClassifier()
# now we need to train the model
# model.fit(X, y)  # this takes two parameters: input set and output set.

# unlike before, instead of passing the entire data set, we want to pass only the training data set
model.fit(X_train, y_train)

# this takes two dimensional array. 
# we are asking our model to make two predictios at the same time.
# passing it two input set, 21 yr old male and 22 yr old female
# predictions = model.predict([ [21, 1], [22, 0] ])
predictions = model.predict(X_test)  # X_test is the data set that contains input values for testing

# to calculate accuracy
# we need to compare the preditions we have with our actual value from output set for testing
# this take two arguments, the expected values and the predictions
# this returns an accuracy score between 0 to 1
score = accuracy_score(y_test, predictions)
score  # returns 1.0 which is 100% accurate

music3.txt

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
import joblib

# import data for model
music_data = pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']

# train it
model = DecisionTreeClassifier()
model.fit(X, y)

# persist the model
joblib.dump(model, 'music-recommender.joblib')

music4.txt

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
import joblib

# this returns our trained model
model = joblib.load('music-recommender.joblib')

# ask it to make predictions
predictions = model.predict([ [21, 1] ])
predictions

music5.txt

# Visualize model decision tree in a graph

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

music_data = pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']

model = DecisionTreeClassifier()
model.fit(X, y)

# .dot format is the graph description language
tree.export_graphviz(
    model, out_file='music-recommender.dot', 
    feature_names=['age', 'gender'], 
    class_names=sorted(y.unique()), 
    label='all', 
    rounded=True, 
    filled=True)