general clasification alg & image recogn

projects/multiai/Classifiers.py

@@ -0,0 +1,261 @@
+import pandas as pd
+
+import matplotlib.pyplot as plt
+
+# from pandas.tools.plotting import scatter_matrix
+
+from pandas.plotting import scatter_matrix
+
+from matplotlib import cm
+
+from sklearn.model_selection import train_test_split
+
+from sklearn.linear_model import LogisticRegression
+
+from sklearn.preprocessing import MinMaxScaler
+
+from sklearn.tree import DecisionTreeClassifier
+
+from sklearn.neighbors import KNeighborsClassifier
+
+from sklearn.linear_model import Lasso
+
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+
+from sklearn.naive_bayes import GaussianNB
+
+from sklearn.svm import SVC
+
+
+
+
+
+
+# Read the table from .txt file
+
+
+
+fruits = pd.read_table('fruit_data_with_colors.txt')
+
+fruits.head()
+
+
+
+# Prepare data for classification
+
+
+
+feature_names = ['mass', 'width', 'height', 'color_score']
+
+X = fruits[feature_names]
+
+y = fruits['fruit_label']
+
+
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+
+
+
+scaler = MinMaxScaler()
+
+X_train = scaler.fit_transform(X_train)
+
+X_test = scaler.transform(X_test)
+
+
+
+# Classifier: logistic regression
+
+
+
+logreg = LogisticRegression()
+
+logreg.fit(X_train, y_train)
+
+print('Accuracy of Logistic regression classifier on training set: {:.2f}'
+
+     .format(logreg.score(X_train, y_train)))
+
+print('Accuracy of Logistic regression classifier on test set: {:.2f}'
+
+     .format(logreg.score(X_test, y_test)))
+
+print(logreg.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(logreg.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+
+
+
+
+# Classifier: Decission tree
+
+
+
+
+
+clf = DecisionTreeClassifier().fit(X_train, y_train)
+
+print('Accuracy of Decision Tree classifier on training set: {:.2f}'
+
+     .format(clf.score(X_train, y_train)))
+
+print('Accuracy of Decision Tree classifier on test set: {:.2f}'
+
+     .format(clf.score(X_test, y_test)))
+
+
+
+print(clf.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(clf.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+
+
+# Classifier: K-Nearest Neighbors
+
+
+
+
+
+knn = KNeighborsClassifier()
+
+knn.fit(X_train, y_train)
+
+print('Accuracy of K-NN classifier on training set: {:.2f}'
+
+     .format(knn.score(X_train, y_train)))
+
+print('Accuracy of K-NN classifier on test set: {:.2f}'
+
+     .format(knn.score(X_test, y_test)))
+
+
+
+print(logreg.predict_proba(X_train))
+
+print(logreg.predict(X_train))
+
+
+
+print(knn.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(knn.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+# Classifier Linear Discriminant Analysis
+
+
+
+lda = LinearDiscriminantAnalysis()
+
+lda.fit(X_train, y_train)
+
+print(X_train)
+
+
+
+print('Accuracy of LDA classifier on training set: {:.2f}'
+
+     .format(lda.score(X_train, y_train)))
+
+print('Accuracy of LDA classifier on test set: {:.2f}'
+
+     .format(lda.score(X_test, y_test)))
+
+
+
+
+
+print(lda.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(lda.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+
+
+# Classifier: Gaussian Naive Bayes
+
+
+
+gnb = GaussianNB()
+
+gnb.fit(X_train, y_train)
+
+print('Accuracy of GNB classifier on training set: {:.2f}'
+
+     .format(gnb.score(X_train, y_train)))
+
+print('Accuracy of GNB classifier on test set: {:.2f}'
+
+     .format(gnb.score(X_test, y_test)))
+
+
+
+print(gnb.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(gnb.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+# Classifier: Support Vector Machine
+
+
+
+svm = SVC(probability=True)
+
+svm.fit(X_train, y_train)
+
+print('Accuracy of SVM classifier on training set: {:.2f}'
+
+     .format(svm.score(X_train, y_train)))
+
+print('Accuracy of SVM classifier on test set: {:.2f}'
+
+     .format(svm.score(X_test, y_test)))
+
+
+
+print(svm.predict_proba([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+print(svm.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))
+
+
+
+#
+# Load the Boston Data Set
+
+# Create training and test split
+#
+# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+#
+# Create an instance of Lasso Regression implementation
+#
+lasso = Lasso(alpha=1.0)
+#
+# Fit the Lasso model
+#
+lasso.fit(X_train, y_train)
+#
+# Create the model score
+#
+# lasso.score(X_test, y_test), lasso.score(X_train, y_train)
+
+
+print('Accuracy of Lasso classifier on training set: {:.2f}'
+
+     .format(lasso.score(X_train, y_train)))
+
+print('Accuracy of Lasso classifier on test set: {:.2f}'
+
+     .format(lasso.score(X_test, y_test)))
+
+# print('Lasso')
+print(lasso.predict([[0.14285714, 0.08823529, 0.69230769, 0.43243243]]))

projects/multiai/README.md

@@ -0,0 +1 @@
+# multiai

projects/multiai/fruit_data_with_colors.txt

@@ -0,0 +1,60 @@
+fruit_label	fruit_name	fruit_subtype	mass	width	height	color_score
+1	apple	granny_smith	192	8.4	7.3	0.55
+1	apple	granny_smith	180	8.0	6.8	0.59
+1	apple	granny_smith	176	7.4	7.2	0.60
+2	mandarin	mandarin	86 	6.2	4.7	0.80
+2	mandarin	mandarin	84 	6.0	4.6	0.79
+2	mandarin	mandarin	80 	5.8	4.3	0.77
+2	mandarin	mandarin	80 	5.9 	4.3	0.81
+2	mandarin	mandarin	76	5.8	4.0	0.81
+1	apple	braeburn	178	7.1	7.8	0.92
+1	apple	braeburn	172	7.4	7.0	0.89
+1	apple	braeburn	166	6.9	7.3	0.93
+1	apple	braeburn	172	7.1	7.6	0.92
+1	apple	braeburn	154	7.0	7.1	0.88
+1	apple	golden_delicious	164	7.3	7.7	0.70
+1	apple	golden_delicious	152	7.6	7.3	0.69
+1	apple	golden_delicious	156	7.7	7.1	0.69
+1	apple	golden_delicious	156	7.6	7.5	0.67
+1	apple	golden_delicious	168	7.5	7.6	0.73
+1	apple	cripps_pink	162	7.5	7.1	0.83
+1	apple	cripps_pink	162	7.4	7.2	0.85
+1	apple	cripps_pink	160	7.5	7.5	0.86
+1	apple	cripps_pink	156	7.4	7.4	0.84
+1	apple	cripps_pink	140	7.3	7.1	0.87
+1	apple	cripps_pink	170	7.6	7.9	0.88
+3	orange	spanish_jumbo	342	9.0	9.4	0.75
+3	orange	spanish_jumbo	356	9.2	9.2	0.75
+3	orange	spanish_jumbo	362	9.6	9.2	0.74
+3	orange	selected_seconds	204	7.5	9.2	0.77
+3	orange	selected_seconds	140	6.7	7.1	0.72
+3	orange	selected_seconds	160	7.0	7.4	0.81
+3	orange	selected_seconds	158	7.1	7.5	0.79
+3	orange	selected_seconds	210	7.8	8.0	0.82
+3	orange	selected_seconds	164	7.2	7.0	0.80
+3	orange	turkey_navel	190	7.5	8.1	0.74
+3	orange	turkey_navel	142	7.6	7.8	0.75
+3	orange	turkey_navel	150	7.1	7.9	0.75
+3	orange	turkey_navel	160	7.1	7.6	0.76
+3	orange	turkey_navel	154	7.3	7.3	0.79
+3	orange	turkey_navel	158	7.2	7.8	0.77
+3	orange	turkey_navel	144	6.8	7.4	0.75
+3	orange	turkey_navel	154	7.1	7.5	0.78
+3	orange	turkey_navel	180	7.6	8.2	0.79
+3	orange	turkey_navel	154	7.2	7.2	0.82
+4	lemon	spanish_belsan	194	7.2	10.3	0.70
+4	lemon	spanish_belsan	200	7.3	10.5	0.72
+4	lemon	spanish_belsan	186	7.2	9.2	0.72
+4	lemon	spanish_belsan	216	7.3	10.2	0.71
+4	lemon	spanish_belsan	196	7.3	9.7	0.72
+4	lemon	spanish_belsan	174	7.3	10.1	0.72
+4	lemon	unknown	132	5.8	8.7	0.73
+4	lemon	unknown	130	6.0	8.2	0.71
+4	lemon	unknown	116	6.0	7.5	0.72
+4	lemon	unknown	118	5.9	8.0	0.72
+4	lemon	unknown	120	6.0	8.4	0.74
+4	lemon	unknown	116	6.1	8.5	0.71
+4	lemon	unknown	116	6.3	7.7	0.72
+4	lemon	unknown	116	5.9	8.1	0.73
+4	lemon	unknown	152	6.5	8.5	0.72
+4	lemon	unknown	118	6.1	8.1	0.70