commit_natalia2

Restaurant/Natalia/Nowy.csv

@@ -1,100 +1,121 @@
-20,0,2,4,3,2
-57,0,8,2,1,2
-50,1,3,4,1,1
-51,1,6,1,1,1
-82,1,9,1,2,2
-73,1,5,4,3,2
-65,0,7,3,2,1
-16,1,9,2,3,1
-23,0,1,4,3,1
-74,0,10,3,1,1
-85,1,5,4,1,2
-35,0,2,1,2,1
-79,1,9,4,1,2
-56,0,7,2,1,2
-51,0,6,4,3,2
-13,1,8,1,3,1
-30,0,8,2,2,2
-50,0,5,5,1,2
-39,1,9,3,3,1
-20,0,7,5,3,1
-63,1,8,4,1,1
-74,1,2,1,3,1
-46,1,7,3,1,2
-52,0,5,3,3,1
-39,0,9,1,3,1
-14,1,4,1,3,2
-81,1,2,1,3,1
-79,0,10,4,1,2
-69,0,1,5,1,2
-87,1,3,4,3,2
-72,1,9,1,3,1
-85,0,5,4,1,2
-59,1,10,5,3,1
-32,1,8,1,3,1
-28,0,3,1,1,2
-77,0,10,3,1,1
-82,1,4,5,3,2
-30,0,9,1,3,2
-83,1,9,2,3,2
-88,1,2,3,2,1
-72,1,8,3,2,1
-87,1,9,2,2,2
-13,0,8,5,2,1
-47,0,6,3,1,2
-51,1,1,4,3,1
-27,0,4,5,2,2
-50,1,7,5,1,2
-16,1,2,4,2,2
-29,0,8,4,3,2
-80,1,2,3,2,1
-16,0,10,2,1,1
-76,0,4,4,3,2
-44,1,6,1,1,2
-63,0,5,2,2,2
-12,1,5,4,3,2
-73,1,1,5,1,2
-39,1,7,3,3,1
-10,0,8,3,1,2
-32,0,7,4,3,1
-32,0,8,1,2,1
-74,1,2,4,1,2
-77,1,9,1,3,1
-13,1,2,1,1,1
-61,0,10,1,1,2
-48,1,2,1,1,1
-11,0,4,5,3,1
-80,0,10,3,3,1
-33,0,9,5,3,2
-53,1,5,2,3,2
-56,0,10,2,2,2
-25,1,4,4,1,2
-27,0,8,3,3,2
-83,0,1,1,1,2
-49,0,4,3,2,2
-76,0,10,3,1,1
-40,0,1,5,2,2
-73,1,3,4,2,1
-19,1,2,4,2,2
-77,1,7,2,3,1
-52,0,5,4,3,2
-29,0,10,2,3,1
-28,1,5,1,3,2
-63,0,1,5,3,2
-84,1,4,2,1,2
-31,0,9,1,3,1
-46,1,3,5,1,1
-84,0,6,5,3,1
-30,0,7,1,2,2
-29,1,7,1,1,1
-46,1,5,3,3,2
-17,1,8,1,1,1
-37,0,10,4,2,1
-43,0,6,1,3,1
-57,1,6,1,2,2
-58,1,4,1,3,2
-59,0,1,4,3,1
-26,0,7,2,3,2
-43,0,2,1,3,1
-66,0,8,2,1,1
-85,1,2,1,2,2
+14,1,3,14,1,2
+7,1,1,11,2,1
+18,1,3,15,1,1
+8,0,2,11,2,3
+11,0,4,12,1,3
+20,0,4,12,1,2
+9,1,1,11,1,2
+7,1,2,15,0,1
+20,1,7,16,1,2
+13,1,2,15,5,4
+39,0,10,11,3,4
+29,1,3,6,5,4
+44,1,7,5,5,4
+65,1,5,4,5,4
+47,1,5,5,5,4
+78,1,0,2,5,4
+73,1,1,4,5,4
+63,1,5,4,5,4
+26,1,9,9,5,4
+38,1,8,5,4,4
+20,1,8,4,4,4
+45,1,8,4,5,4
+50,1,8,6,4,4
+45,1,9,6,5,4
+35,1,8,8,5,4
+29,1,3,6,5,5
+29,0,9,9,5,5
+15,0,5,4,4,5
+20,0,4,4,5,5
+25,0,4,4,4,5
+30,0,6,4,4,5
+35,0,7,6,4,5
+45,0,6,5,4,5
+44,1,7,5,4,6
+44,1,7,5,3,6
+30,0,7,5,3,6
+10,1,6,5,3,6
+15,1,7,5,3,6
+17,0,5,5,3,6
+25,1,6,4,4,6
+46,1,6,3,4,6
+65,1,5,4,0,7
+10,0,5,4,1,7
+15,0,5,4,0,7
+16,1,5,4,0,7
+17,1,5,4,1,7
+16,0,5,4,0,7
+20,0,5,4,1,7
+21,0,5,4,0,7
+25,1,5,4,0,7
+27,1,5,4,0,7
+28,1,5,4,1,7
+29,1,5,4,1,7
+29,1,5,4,0,7
+29,0,5,4,0,7
+30,0,5,4,0,7
+31,1,5,4,0,7
+32,1,6,3,0,7
+34,1,6,4,0,7
+35,1,6,4,1,7
+46,1,5,4,1,7
+47,1,5,4,1,7
+47,0,5,4,1,7
+47,0,5,4,0,7
+48,1,5,4,1,7
+48,1,5,4,0,7
+48,0,5,4,1,7
+49,1,5,4,1,7
+49,0,5,4,1,7
+7,0,3,10,0,1
+8,0,3,10,0,1
+10,1,4,10,0,1
+10,0,2,9,0,1
+9,1,3,9,0,1
+13,1,3,10,0,1
+13,1,4,9,0,1
+15,0,2,8,0,1
+14,1,2,8,0,1
+16,1,3,8,0,1
+16,1,3,9,1,1
+16,0,3,9,1,1
+16,0,4,8,1,1
+16,1,4,10,1,1
+30,0,4,8,0,1
+30,1,4,8,0,1
+30,1,5,9,1,1
+30,0,3,10,1,1
+31,0,3,9,0,1
+31,0,4,9,1,1
+31,1,3,10,0,1
+17,0,15,7,2,2
+17,0,14,7,2,2
+17,0,14,10,1,2
+17,0,13,10,1,2
+17,1,14,10,2,2
+17,1,15,7,1,2
+18,0,13,7,2,2
+18,0,15,7,1,2
+18,1,13,7,1,2
+20,0,14,8,3,2
+20,1,13,7,3,2
+21,1,15,5,1,2
+21,0,13,6,2,2
+30,0,13,6,2,2
+30,0,15,5,1,2
+30,0,14,6,1,2
+31,0,15,5,1,2
+31,1,15,4,2,2
+31,1,14,6,2,2
+31,1,14,5,0,2
+20,1,10,3,0,3
+20,1,9,4,0,3
+21,1,10,3,0,3
+21,0,9,4,0,3
+21,0,10,5,0,3
+30,0,10,5,0,3
+40,0,10,5,0,3
+50,0,10,5,0,3
+65,0,10,5,0,3
+21,0,11,4,5,4
+22,1,11,4,5,4

Restaurant/Natalia/Tree_natalia

@@ -1,54 +0,0 @@
-# Load libraries
-import pandas as pd
-from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier
-from sklearn.model_selection import train_test_split # Import train_test_split function
-from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation
-from sklearn.tree import export_graphviz
-from sklearn.externals.six import StringIO
-from IPython.display import Image
-import pydotplus
-
-col_names = ['age', 'sex', 'fat', 'spicy', 'hungry', 'budget']
-# load dataset
-pima = pd.read_csv("nazwa.csv", header=None, names=col_names)
-
-#split dataset in features and target variable
-feature_cols = ['age', 'sex', 'fat', 'spicy']
-X = pima[feature_cols] # Features
-y = pima.label # Target variable
-
-# Split dataset into training set and test set
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1) # 70% training and 30% test
-
-# Create Decision Tree classifer object
-clf = DecisionTreeClassifier()
-
-# Train Decision Tree Classifer
-clf = clf.fit(X_train,y_train)
-
-#Predict the response for test dataset
-y_pred = clf.predict(X_test)
-
-# Model Accuracy, how often is the classifier correct?
-print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
-
-dot_data = StringIO()
-export_graphviz(clf, out_file=dot_data,
-                filled=True, rounded=True,
-                special_characters=True,feature_names = feature_cols,class_names=['0','1'])
-graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
-graph.write_png('food_tree.png')
-Image(graph.create_png())
-
-
-# Create Decision Tree classifer object
-clf = DecisionTreeClassifier(criterion="entropy", max_depth=3)
-
-# Train Decision Tree Classifer
-clf = clf.fit(X_train,y_train)
-
-#Predict the response for test dataset
-y_pred = clf.predict(X_test)
-
-# Model Accuracy, how often is the classifier correct?
-print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Restaurant/Natalia/__init__.py

@@ -0,0 +1,87 @@
+import pandas as pd
+try:
+    from StringIO import StringIO
+except ImportError:
+    from io import StringIO
+from io import StringIO
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.model_selection import train_test_split
+from sklearn import metrics
+from sklearn.tree import export_graphviz
+import joblib
+from IPython.display import Image
+import pydotplus
+import os
+os.environ["PATH"] += os.pathsep + r'C:\Program Files (x86)\Graphviz2.38\bin'
+
+def main():
+    dot_data = StringIO()
+    col_names = ['age', 'sex', 'fat', 'fiber', 'spicy', 'number']
+    #import danych
+    model_tree = pd.read_csv("Nowy.csv", header=None, names=col_names)
+    model_tree.head()
+    #seperacja danych cechy
+    feature_cols = ['age', 'sex', 'fat', 'fiber', 'spicy']
+    X = model_tree[feature_cols]
+    #separacja danych etykieta
+    y = model_tree.number
+    # Target variable
+
+    #podział danych na zestaw treningowy i testowy; 70% trening 30% test
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,
+                                                        random_state=1)  # 70% training and 30% test
+
+    ###############################
+    # stworzenie -obiektu- drzewa Decision Tree classifer
+    clf = DecisionTreeClassifier()
+
+    # drzewo treningowe
+    clf = clf.fit(X_train, y_train)
+
+    #generowanie wyników dla zbioru testowego
+    y_pred = clf.predict(X_test)
+    #print(y_pred)
+
+    #Akuratność dla modelu danych
+    print("Accuracy:", metrics.accuracy_score(y_test, y_pred))
+
+    dot_data = StringIO()
+    #tworzenie graficznego drzewa
+    export_graphviz(clf, out_file=dot_data,
+                    filled=True, rounded=True,
+                    special_characters=True, feature_names=feature_cols,
+                    class_names=['1', '2', '3', '4', '5', '6', '7'])
+    graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
+    graph.write_png('polecanie_1.png')
+    Image(graph.create_png())
+
+    # ************************************************************
+    # stworzenie -obiektu- drzewa Decision Tree classifer z kryterium entropii
+    clf = DecisionTreeClassifier(criterion="entropy")
+
+    #drzewo testowe-z entripią
+    clf = clf.fit(X_train, y_train)
+
+    #generowanie wyników dla zbioru testowego
+    y_pred = clf.predict(X_test)
+
+    #Akuratność dla modelu danych z warunkiem entropii
+    print("Accuracy:", metrics.accuracy_score(y_test, y_pred))
+
+    #stowrzenie graficznego drzewa z warunkiem entropii
+    dot_data = StringIO()
+    export_graphviz(clf, out_file=dot_data,
+                    filled=True, rounded=True,
+                    special_characters=True, feature_names=feature_cols,
+                    class_names=['1', '2', '3', '4', '5', '6', '7'])
+    graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
+    graph.write_png('polecanie_2_entropia.png')
+    Image(graph.create_png())
+
+    #zapisanie modelu danych do pliku
+    file_name = 'final_model.sav'
+    joblib.dump(clf, file_name)
+
+    return
+
+main()