My experience with Python and machine Learning

Using Jupyter Notebook with anaconda3 Docker image, pull from docker pull continuumio/anaconda3

%matplotlib notebook 
import numpy as np 
import matplotlib.pyplot as plt 
import pandas as pd 
from sklearn.model_selection import  train_test_split
fruits = pd.read_table('/home/Fruits/data.txt')

fruits.head()

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; }

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	fruit_label	fruit_name	mass	width	height
0	1	apple	192	8.4	7.3
1	1	apple	180	8.0	6.8
2	1	apple	176	7.4	7.2
3	2	Mandarin	86	6.2	4.7
4	2	Mandarin	84	6.0	4.6

look_up_fruit_name = dict(zip(fruits.fruit_label.unique(), fruits.fruit_name.unique()))
look_up_fruit_name 

{1: 'apple',
 2: 'Mandarin',
 3: 'Braeburn',
 4: 'Golden',
 5: 'Cripps',
 6: 'Lane',
 7: 'Morrisons',
 8: 'Turkey',
 9: 'Belsan',
 10: 'lemons'}

X = fruits[['mass', 'width', 'height']]
y = fruits['fruit_label']

X_train, X_test, y_train, y_test = train_test_split(X, y)

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(X_train, y_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform')

knn.score(X_test, y_test)

0.4666666666666667

fruit_prediction = knn.predict([[20, 4.5, 5.5]])
print(fruit_prediction[0])
look_up_fruit_name[fruit_prediction[0]]

2





'Mandarin'

fruit_prediction = knn.predict([[100, 6.5, 8.5]])
print(fruit_prediction[0])
look_up_fruit_name[fruit_prediction[0]]

10





'lemons'

from sklearn.metrics import classification_report
pred = knn.predict(X_test)
print(classification_report(y_test, pred))

             precision    recall  f1-score   support

          1       0.00      0.00      0.00         1
          2       1.00      1.00      1.00         2
          3       0.00      0.00      0.00         1
          4       0.00      0.00      0.00         1
          5       0.00      0.00      0.00         1
          7       0.00      0.00      0.00         2
          8       1.00      0.33      0.50         3
          9       0.00      0.00      0.00         0
         10       1.00      1.00      1.00         4

avg / total       0.60      0.47      0.50        15



/opt/conda/lib/python3.6/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/opt/conda/lib/python3.6/site-packages/sklearn/metrics/classification.py:1137: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples.
  'recall', 'true', average, warn_for)

k_range = range(1,20)
score = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train, y_train)
    score.append(knn.score(X_test, y_test))
plt.figure()
plt.xlabel('k')
plt.ylabel('accuracy')
plt.scatter(k_range, score)
plt.xticks([0, 5, 10, 15, 20])

<IPython.core.display.Javascript object>

([<matplotlib.axis.XTick at 0x7f242d31f6a0>,
  <matplotlib.axis.XTick at 0x7f242d38ef98>,
  <matplotlib.axis.XTick at 0x7f242d38ee80>,
  <matplotlib.axis.XTick at 0x7f242d33ca58>,
  <matplotlib.axis.XTick at 0x7f242d33cf28>],
 <a list of 5 Text xticklabel objects>)