added files

2021-11-11 11:01:58 +01:00
parent ea69981166
commit 05d5824904
13 changed files with 4025 additions and 0 deletions
@@ -0,0 +1,57 @@
+digraph Tree {
+node [shape=box, style="filled, rounded", color="black", fontname=helvetica] ;
+edge [fontname=helvetica] ;
+0 [label="worst perimeter <= 106.05\ngini = 0.465\nsamples = 426\nvalue = [[269, 157]\n[157, 269]]", fillcolor="#e5813908"] ;
+1 [label="worst concave points <= 0.159\ngini = 0.067\nsamples = 259\nvalue = [[250, 9]\n[9, 250]]", fillcolor="#e58139db"] ;
+0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
+2 [label="worst concave points <= 0.135\ngini = 0.031\nsamples = 253\nvalue = [[249, 4]\n[4, 249]]", fillcolor="#e58139ee"] ;
+1 -> 2 ;
+3 [label="radius error <= 0.643\ngini = 0.008\nsamples = 242\nvalue = [[241, 1]\n[1, 241]]", fillcolor="#e58139fb"] ;
+2 -> 3 ;
+4 [label="gini = 0.0\nsamples = 239\nvalue = [[239, 0]\n[0, 239]]", fillcolor="#e58139ff"] ;
+3 -> 4 ;
+5 [label="worst symmetry <= 0.208\ngini = 0.444\nsamples = 3\nvalue = [[2, 1]\n[1, 2]]", fillcolor="#e5813913"] ;
+3 -> 5 ;
+6 [label="gini = 0.0\nsamples = 1\nvalue = [[0, 1]\n[1, 0]]", fillcolor="#e58139ff"] ;
+5 -> 6 ;
+7 [label="gini = 0.0\nsamples = 2\nvalue = [[2, 0]\n[0, 2]]", fillcolor="#e58139ff"] ;
+5 -> 7 ;
+8 [label="worst texture <= 29.455\ngini = 0.397\nsamples = 11\nvalue = [[8, 3]\n[3, 8]]", fillcolor="#e581392c"] ;
+2 -> 8 ;
+9 [label="gini = 0.0\nsamples = 8\nvalue = [[8, 0]\n[0, 8]]", fillcolor="#e58139ff"] ;
+8 -> 9 ;
+10 [label="gini = 0.0\nsamples = 3\nvalue = [[0, 3]\n[3, 0]]", fillcolor="#e58139ff"] ;
+8 -> 10 ;
+11 [label="mean texture <= 16.22\ngini = 0.278\nsamples = 6\nvalue = [[1, 5]\n[5, 1]]", fillcolor="#e581396b"] ;
+1 -> 11 ;
+12 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139ff"] ;
+11 -> 12 ;
+13 [label="gini = 0.0\nsamples = 5\nvalue = [[0, 5]\n[5, 0]]", fillcolor="#e58139ff"] ;
+11 -> 13 ;
+14 [label="worst texture <= 20.645\ngini = 0.202\nsamples = 167\nvalue = [[19, 148]\n[148, 19]]", fillcolor="#e5813994"] ;
+0 -> 14 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
+15 [label="worst radius <= 17.74\ngini = 0.375\nsamples = 16\nvalue = [[12, 4]\n[4, 12]]", fillcolor="#e5813938"] ;
+14 -> 15 ;
+16 [label="gini = 0.0\nsamples = 11\nvalue = [[11, 0]\n[0, 11]]", fillcolor="#e58139ff"] ;
+15 -> 16 ;
+17 [label="mean texture <= 13.745\ngini = 0.32\nsamples = 5\nvalue = [[1, 4]\n[4, 1]]", fillcolor="#e5813955"] ;
+15 -> 17 ;
+18 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139ff"] ;
+17 -> 18 ;
+19 [label="gini = 0.0\nsamples = 4\nvalue = [[0, 4]\n[4, 0]]", fillcolor="#e58139ff"] ;
+17 -> 19 ;
+20 [label="mean concave points <= 0.049\ngini = 0.088\nsamples = 151\nvalue = [[7, 144]\n[144, 7]]", fillcolor="#e58139d0"] ;
+14 -> 20 ;
+21 [label="concave points error <= 0.01\ngini = 0.48\nsamples = 15\nvalue = [[6, 9]\n[9, 6]]", fillcolor="#e5813900"] ;
+20 -> 21 ;
+22 [label="gini = 0.0\nsamples = 9\nvalue = [[0, 9]\n[9, 0]]", fillcolor="#e58139ff"] ;
+21 -> 22 ;
+23 [label="gini = 0.0\nsamples = 6\nvalue = [[6, 0]\n[0, 6]]", fillcolor="#e58139ff"] ;
+21 -> 23 ;
+24 [label="worst smoothness <= 0.096\ngini = 0.015\nsamples = 136\nvalue = [[1, 135]\n[135, 1]]", fillcolor="#e58139f7"] ;
+20 -> 24 ;
+25 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139ff"] ;
+24 -> 25 ;
+26 [label="gini = 0.0\nsamples = 135\nvalue = [[0, 135]\n[135, 0]]", fillcolor="#e58139ff"] ;
+24 -> 26 ;
+}
@@ -0,0 +1,68 @@
+# Common imports
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.tree import export_graphviz
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
+from IPython.display import Image 
+from pydot import graph_from_dot_data
+import os
+
+# Where to save the figures and data files
+PROJECT_ROOT_DIR = "Results"
+FIGURE_ID = "Results/FigureFiles"
+DATA_ID = "DataFiles/"
+
+if not os.path.exists(PROJECT_ROOT_DIR):
+    os.mkdir(PROJECT_ROOT_DIR)
+
+if not os.path.exists(FIGURE_ID):
+    os.makedirs(FIGURE_ID)
+
+if not os.path.exists(DATA_ID):
+    os.makedirs(DATA_ID)
+
+def image_path(fig_id):
+    return os.path.join(FIGURE_ID, fig_id)
+
+def data_path(dat_id):
+    return os.path.join(DATA_ID, dat_id)
+
+def save_fig(fig_id):
+    plt.savefig(image_path(fig_id) + ".png", format='png')
+
+infile = open(data_path("grades.csv"),'r')
+
+# Read the experimental data with Pandas
+from IPython.display import display
+grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.DataFrame(grades)
+
+# Features and targets
+X = grades.loc[:, grades.columns != 'Grade'].values
+y = grades.loc[:, grades.columns == 'Grade'].values
+
+# Create the encoder.
+encoder = OneHotEncoder(handle_unknown="ignore")
+# Assume for simplicity all features are categorical.
+encoder.fit(X)    
+# Apply the encoder.
+X = encoder.transform(X)
+print(X)
+# Then do a Classification tree
+tree_clf = DecisionTreeClassifier(max_depth=2)
+tree_clf.fit(X, y)
+print("Train set accuracy with Decision Tree: {:.2f}".format(tree_clf.score(X,y)))
+#transfer to a decision tree graph
+export_graphviz(
+    tree_clf,
+    out_file="DataFiles/grade.dot",
+    rounded=True,
+    filled=True
+)
+cmd = 'dot -Tpng DataFiles/cancer.dot -o DataFiles/grades.png'
+os.system(cmd)
+
@@ -0,0 +1,11 @@
+Trend,Sleep,Studie,Grade
+1,0,0,1
+0,1,0,0
+1,0,1,1
+1,1,1,1
+0,0,1,0
+1,0,0,0
+0,1,1,0
+0,0,1,0
+1,0,0,0
+1,1,1,1
@@ -0,0 +1,15 @@
+Day,Outlook,Temperature,Humidity,Wind,Ride
+1,Sunny,Hot,High,Weak,0
+2,Sunny,Hot,High,Strong,1
+3,Overcast,Hot,High,Weak,1
+4,Rain,Mild,High,Weak,1
+5,Rain,Cool,Normal,Weak,1
+6,Rain,Cool,Normal,Strong,0
+7,Overcast,Cool,Normal,Strong,1
+8,Sunny,Mild,High,Weak,0
+9,Sunny,Cool,Normal,Weak,1
+10,Rain,Mild,Normal,Weak,1
+11,Sunny,Mild,Normal,Strong,1
+12,Overcast,Mild,High,Strong,1
+13,Overcast,Hot,Normal,Weak,1
+14,Rain,Mild,High,Strong,0
@@ -0,0 +1,15 @@
+Outlook,Temperature,Humidity,Wind,Ride
+0,0,0,0,0
+0,0,0,1,1
+1,0,0,0,1
+2,1,0,0,1
+2,2,1,0,1
+2,2,1,1,0
+1,2,1,1,1
+0,1,0,0,0
+0,2,1,0,1
+2,1,1,0,1
+0,1,1,1,1
+1,1,0,1,1
+1,0,1,0,1
+2,1,0,1,0
@@ -0,0 +1,15 @@
+Outlook,Temperature,Humidity,Wind,Ride
+Sunny,Hot,High,Weak,0
+Sunny,Hot,High,Strong,1
+Overcast,Hot,High,Weak,1
+Rain,Mild,High,Weak,1
+Rain,Cool,Normal,Weak,1
+Rain,Cool,Normal,Strong,0
+Overcast,Cool,Normal,Strong,1
+Sunny,Mild,High,Weak,0
+Sunny,Cool,Normal,Weak,1
+Rain,Mild,Normal,Weak,1
+Sunny,Mild,Normal,Strong,1
+Overcast,Mild,High,Strong,1
+Overcast,Hot,Normal,Weak,1
+Rain,Mild,High,Strong,0
@@ -0,0 +1,13 @@
+digraph Tree {
+node [shape=box, style="filled, rounded", color="black", fontname=helvetica] ;
+edge [fontname=helvetica] ;
+0 [label="X[7] <= 0.5\ngini = 0.48\nsamples = 15\nvalue = [4, 10, 1]", fillcolor="#39e5818b"] ;
+1 [label="X[1] <= 0.5\ngini = 0.408\nsamples = 14\nvalue = [4, 10, 0]", fillcolor="#39e58199"] ;
+0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
+2 [label="gini = 0.48\nsamples = 10\nvalue = [4, 6, 0]", fillcolor="#39e58155"] ;
+1 -> 2 ;
+3 [label="gini = 0.0\nsamples = 4\nvalue = [0, 4, 0]", fillcolor="#39e581ff"] ;
+1 -> 3 ;
+4 [label="gini = 0.0\nsamples = 1\nvalue = [0, 0, 1]", fillcolor="#8139e5ff"] ;
+0 -> 4 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
+}
@@ -0,0 +1,15 @@
+Day,Outlook,Temperature,Humidity,Wind,Ride
+1,Sunny,Hot,High,Weak,0
+2,Sunny,Hot,High,Strong,1
+3,Overcast,Hot,High,Weak,1
+4,Rain,Mild,High,Weak,1
+5,Rain,Cool,Normal,Weak,1
+6,Rain,Cool,Normal,Strong,0
+7,Overcast,Cool,Normal,Strong,1
+8,Sunny,Mild,High,Weak,0
+9,Sunny,Cool,Normal,Weak,1
+10,Rain,Mild,Normal,Weak,1
+11,Sunny,Mild,Normal,Strong,1
+12,Overcast,Mild,High,Strong,1
+13,Overcast,Hot,Normal,Weak,1
+14,Rain,Mild,High,Strong,0
@@ -0,0 +1,101 @@
+aardvark,1,0,0,1,0,0,1,1,1,1,0,0,4,0,0,1,1
+antelope,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+bass,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,0,4
+bear,1,0,0,1,0,0,1,1,1,1,0,0,4,0,0,1,1
+boar,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+buffalo,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+calf,1,0,0,1,0,0,0,1,1,1,0,0,4,1,1,1,1
+carp,0,0,1,0,0,1,0,1,1,0,0,1,0,1,1,0,4
+catfish,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,0,4
+cavy,1,0,0,1,0,0,0,1,1,1,0,0,4,0,1,0,1
+cheetah,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+chicken,0,1,1,0,1,0,0,0,1,1,0,0,2,1,1,0,2
+chub,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,0,4
+clam,0,0,1,0,0,0,1,0,0,0,0,0,0,0,0,0,7
+crab,0,0,1,0,0,1,1,0,0,0,0,0,4,0,0,0,7
+crayfish,0,0,1,0,0,1,1,0,0,0,0,0,6,0,0,0,7
+crow,0,1,1,0,1,0,1,0,1,1,0,0,2,1,0,0,2
+deer,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+dogfish,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,1,4
+dolphin,0,0,0,1,0,1,1,1,1,1,0,1,0,1,0,1,1
+dove,0,1,1,0,1,0,0,0,1,1,0,0,2,1,1,0,2
+duck,0,1,1,0,1,1,0,0,1,1,0,0,2,1,0,0,2
+elephant,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+flamingo,0,1,1,0,1,0,0,0,1,1,0,0,2,1,0,1,2
+flea,0,0,1,0,0,0,0,0,0,1,0,0,6,0,0,0,6
+frog,0,0,1,0,0,1,1,1,1,1,0,0,4,0,0,0,5
+frog,0,0,1,0,0,1,1,1,1,1,1,0,4,0,0,0,5
+fruitbat,1,0,0,1,1,0,0,1,1,1,0,0,2,1,0,0,1
+giraffe,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+girl,1,0,0,1,0,0,1,1,1,1,0,0,2,0,1,1,1
+gnat,0,0,1,0,1,0,0,0,0,1,0,0,6,0,0,0,6
+goat,1,0,0,1,0,0,0,1,1,1,0,0,4,1,1,1,1
+gorilla,1,0,0,1,0,0,0,1,1,1,0,0,2,0,0,1,1
+gull,0,1,1,0,1,1,1,0,1,1,0,0,2,1,0,0,2
+haddock,0,0,1,0,0,1,0,1,1,0,0,1,0,1,0,0,4
+hamster,1,0,0,1,0,0,0,1,1,1,0,0,4,1,1,0,1
+hare,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,0,1
+hawk,0,1,1,0,1,0,1,0,1,1,0,0,2,1,0,0,2
+herring,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,0,4
+honeybee,1,0,1,0,1,0,0,0,0,1,1,0,6,0,1,0,6
+housefly,1,0,1,0,1,0,0,0,0,1,0,0,6,0,0,0,6
+kiwi,0,1,1,0,0,0,1,0,1,1,0,0,2,1,0,0,2
+ladybird,0,0,1,0,1,0,1,0,0,1,0,0,6,0,0,0,6
+lark,0,1,1,0,1,0,0,0,1,1,0,0,2,1,0,0,2
+leopard,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+lion,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+lobster,0,0,1,0,0,1,1,0,0,0,0,0,6,0,0,0,7
+lynx,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+mink,1,0,0,1,0,1,1,1,1,1,0,0,4,1,0,1,1
+mole,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,0,1
+mongoose,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+moth,1,0,1,0,1,0,0,0,0,1,0,0,6,0,0,0,6
+newt,0,0,1,0,0,1,1,1,1,1,0,0,4,1,0,0,5
+octopus,0,0,1,0,0,1,1,0,0,0,0,0,8,0,0,1,7
+opossum,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,0,1
+oryx,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,1,1
+ostrich,0,1,1,0,0,0,0,0,1,1,0,0,2,1,0,1,2
+parakeet,0,1,1,0,1,0,0,0,1,1,0,0,2,1,1,0,2
+penguin,0,1,1,0,0,1,1,0,1,1,0,0,2,1,0,1,2
+pheasant,0,1,1,0,1,0,0,0,1,1,0,0,2,1,0,0,2
+pike,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,1,4
+piranha,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,0,4
+pitviper,0,0,1,0,0,0,1,1,1,1,1,0,0,1,0,0,3
+platypus,1,0,1,1,0,1,1,0,1,1,0,0,4,1,0,1,1
+polecat,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+pony,1,0,0,1,0,0,0,1,1,1,0,0,4,1,1,1,1
+porpoise,0,0,0,1,0,1,1,1,1,1,0,1,0,1,0,1,1
+puma,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+pussycat,1,0,0,1,0,0,1,1,1,1,0,0,4,1,1,1,1
+raccoon,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+reindeer,1,0,0,1,0,0,0,1,1,1,0,0,4,1,1,1,1
+rhea,0,1,1,0,0,0,1,0,1,1,0,0,2,1,0,1,2
+scorpion,0,0,0,0,0,0,1,0,0,1,1,0,8,1,0,0,7
+seahorse,0,0,1,0,0,1,0,1,1,0,0,1,0,1,0,0,4
+seal,1,0,0,1,0,1,1,1,1,1,0,1,0,0,0,1,1
+sealion,1,0,0,1,0,1,1,1,1,1,0,1,2,1,0,1,1
+seasnake,0,0,0,0,0,1,1,1,1,0,1,0,0,1,0,0,3
+seawasp,0,0,1,0,0,1,1,0,0,0,1,0,0,0,0,0,7
+skimmer,0,1,1,0,1,1,1,0,1,1,0,0,2,1,0,0,2
+skua,0,1,1,0,1,1,1,0,1,1,0,0,2,1,0,0,2
+slowworm,0,0,1,0,0,0,1,1,1,1,0,0,0,1,0,0,3
+slug,0,0,1,0,0,0,0,0,0,1,0,0,0,0,0,0,7
+sole,0,0,1,0,0,1,0,1,1,0,0,1,0,1,0,0,4
+sparrow,0,1,1,0,1,0,0,0,1,1,0,0,2,1,0,0,2
+squirrel,1,0,0,1,0,0,0,1,1,1,0,0,2,1,0,0,1
+starfish,0,0,1,0,0,1,1,0,0,0,0,0,5,0,0,0,7
+stingray,0,0,1,0,0,1,1,1,1,0,1,1,0,1,0,1,4
+swan,0,1,1,0,1,1,0,0,1,1,0,0,2,1,0,1,2
+termite,0,0,1,0,0,0,0,0,0,1,0,0,6,0,0,0,6
+toad,0,0,1,0,0,1,0,1,1,1,0,0,4,0,0,0,5
+tortoise,0,0,1,0,0,0,0,0,1,1,0,0,4,1,0,1,3
+tuatara,0,0,1,0,0,0,1,1,1,1,0,0,4,1,0,0,3
+tuna,0,0,1,0,0,1,1,1,1,0,0,1,0,1,0,1,4
+vampire,1,0,0,1,1,0,0,1,1,1,0,0,2,1,0,0,1
+vole,1,0,0,1,0,0,0,1,1,1,0,0,4,1,0,0,1
+vulture,0,1,1,0,1,0,1,0,1,1,0,0,2,1,0,1,2
+wallaby,1,0,0,1,0,0,0,1,1,1,0,0,2,1,0,1,1
+wasp,1,0,1,0,1,0,0,0,0,1,1,0,6,0,0,0,6
+wolf,1,0,0,1,0,0,1,1,1,1,0,0,4,1,0,1,1
+worm,0,0,1,0,0,0,0,0,0,1,0,0,0,0,0,0,7
+wren,0,1,1,0,1,0,0,0,1,1,0,0,2,1,0,0,2