Machine Learning Software that predicts planet

Machine Learning Software that predicts planets based on their distance from the sun, number of satellites and various properties I developed Machine Learning Software that predicts planets based on their distance from the sun, number of satellites and various properties. This machine learning software is based on Random Forest Classifier and Random Forest Regression. Based on the principles of Supervised Learning, machine learning software predicts planets by their distance from the sun, Confirmed Moons, Provisional Moons, Total Moons, Volume (cubic kilometers) and planet's diameter.
emirhanai · Aug 29, 2021 · 5e9d3d7 · 5e9d3d7
1 parent 6389dac
commit 5e9d3d7
Show file tree

Hide file tree

Showing 16 changed files with 147 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -1,2 +1,52 @@
-# Machine-Learning-Software-that-predicts-planets-based-on-their-distance-from-the-sun-number-of-sate
-Machine Learning Software that predicts planets based on their distance from the sun, number of satellites and various properties
+# **Machine Learning Software that predicts planets based on their distance from the sun, number of satellites and various properties**
+I developed Machine Learning Software that predicts planets based on their distance from the sun, number of satellites and various properties. This machine learning software is based on Random Forest Classifier and Random Forest Regression. Based on the principles of Supervised Learning, machine learning software predicts planets by their distance from the sun, Confirmed Moons, Provisional Moons, Total Moons, Volume (cubic kilometers) and planet's diameter.
+
+The values you enter should be (respectively):
+
+**1) Enter to Distance From The Sun**
+
+**2) Enter to Confirmed Moons**
+
+**3) Enter to Provisional Moons**
+
+**4) Enter to Total Moons** 
+
+**5) Enter to Volume (Enter the state / 1.000.000.000) - Cubic (km)**
+
+**6) Enter to Diameter Of Planet (km)**
+
+
+_Example:_ `model_run = model.predict([[Distance_From_The_Sun,Confirmed_Moons, Provisional_Moons, Total_Moons, Volume_1000000000_cubic_km, Diameter_of_Planet_km]])`
+
+_Outpot :_ `Predicted Planet: ['Mercury']`
+
+**I am happy to present this software to you!**
+
+Data Source: [DataSource] , [DataSource1]
+###**The coding language used:**
+
+`Python 3.9.6`
+
+###**Libraries Used:**
+
+`Sklearn`
+
+`Pandas`
+
+### **Developer Information:**
+
+Name-Surname: **Emirhan BULUT**
+
+Contact (Email) : **emirhan.bulut@turkiyeyapayzeka.com**
+
+LinkedIn : **[https://www.linkedin.com/in/artificialintelligencebulut/][LinkedinAccount]**
+
+[LinkedinAccount]: https://www.linkedin.com/in/artificialintelligencebulut/
+
+Official Website: **[https://www.emirhanbulut.com.tr][OfficialWebSite]**
+
+[OfficialWebSite]: https://www.emirhanbulut.com.tr
+
+[DataSource]: https://www.nasa.gov/
+
+[DataSource1]: https://en.wikipedia.org/wiki/Main_Page
diff --git a/emirhan_project_planet_classifier0.png b/emirhan_project_planet_classifier0.png
diff --git a/emirhan_project_planet_classifier1.png b/emirhan_project_planet_classifier1.png
diff --git a/emirhan_project_planet_classifier2.png b/emirhan_project_planet_classifier2.png
diff --git a/emirhan_project_planet_classifier3.png b/emirhan_project_planet_classifier3.png
diff --git a/emirhan_project_planet_classifier4.png b/emirhan_project_planet_classifier4.png
diff --git a/emirhan_project_planet_classifier5.png b/emirhan_project_planet_classifier5.png
diff --git a/emirhan_project_planet_regressor0.png b/emirhan_project_planet_regressor0.png
diff --git a/emirhan_project_planet_regressor1.png b/emirhan_project_planet_regressor1.png
diff --git a/emirhan_project_planet_regressor2.png b/emirhan_project_planet_regressor2.png
diff --git a/emirhan_project_planet_regressor3.png b/emirhan_project_planet_regressor3.png
diff --git a/emirhan_project_planet_regressor4.png b/emirhan_project_planet_regressor4.png
diff --git a/emirhan_project_planet_regressor5.png b/emirhan_project_planet_regressor5.png
diff --git a/planet_prediction.py b/planet_prediction.py
@@ -0,0 +1,85 @@
+from sklearn.preprocessing import LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.tree import export_graphviz
+import pandas as pd
+
+def save_decision_trees_as_dot(clf, iteration, feature_name, target_name):
+    file_name = open("emirhan_project_planet" + str(iteration) + ".dot",'w')
+    dot_data = export_graphviz(
+        clf,
+        out_file=file_name,
+        feature_names=feature_name,
+        class_names=target_name,
+        rounded=True,
+        proportion=False,
+        precision=2,
+        filled=True,)
+    file_name.close()
+    print("Decision Tree in forest :) {} saved as dot file".format(iteration + 1))
+
+
+df = pd.read_csv('planets_large_data.csv')
+
+X= df.drop(['Planet'], axis = 'columns')
+#print(X)
+y= df.drop(['Distance From The Sun','Confirmed Moons','Provisional Moons','Total Moons','(Volume/1000000000-cubic km)','Diameter of Planet(km)'], axis= 'columns')
+#print(y)
+
+y_data = LabelEncoder()
+#LabelEncoder() function :))
+
+y['Planet_Data'] = y_data.fit_transform(y['Planet'])
+# Planet Columns value change to Planet_Data with fit_transform function
+
+#print(connects)
+
+y_n = y.drop(['Planet'],axis='columns')
+#New Columns of Target :))
+
+# In additionnn: print(y_n)
+
+
+feature_names = X.columns
+#a few fetaure names..
+
+target_names = y_n.columns
+# one of the columns is target name :)
+
+model = RandomForestClassifier(n_estimators=1)
+
+# our model like to above :)
+
+model.fit(X,y_n)
+#our model training to the above...
+
+#print(model.estimators_[2])
+
+#The collection of fitted sub-estimators = estimators_
+
+for i in range(len(model.estimators_)):
+    save_decision_trees_as_dot(model.estimators_[i], i, feature_names, target_names)
+    print(i)
+
+
+#prediction is the PLANET!
+
+
+Distance_From_The_Sun = int(input("Enter to Distance From The Sun: "))
+Confirmed_Moons = int(input("Enter to Confirmed Moons: "))
+Provisional_Moons = int(input("Enter to Provisional Moons: "))
+Total_Moons = int(input("Enter to Total Moons: "))
+Volume_1000000000_cubic_km = int(input("Enter to Volume (Enter the state / 1.000.000.000) - Cubic (km) : "))
+Diameter_of_Planet_km = int(input("Enter to Diameter Of Planet (km): "))
+
+try:
+    while True:
+        model_run = model.predict([[Distance_From_The_Sun,Confirmed_Moons, Provisional_Moons, Total_Moons, Volume_1000000000_cubic_km, Diameter_of_Planet_km]])
+        planets = pd.read_csv('planets_name.csv',index_col=None, na_values=None)
+        planet_detect_algorithm = planets.columns.values[model_run]
+        print("Predicted Planet: {}".format(planet_detect_algorithm))
+        break
+
+except:
+    print("Try again!")
+#print(model.predict([[predict_2014,predict_2020,predict_population]]))
diff --git a/planets_large_data.csv b/planets_large_data.csv
@@ -0,0 +1,9 @@
+Planet,Distance From The Sun,Confirmed Moons,Provisional Moons,Total Moons,(Volume/1000000000-cubic km),Diameter of Planet(km)
+Mercury,57910000,0,0,0,60,4884
+Venus,108200000,0,0,0,928,12342
+Earth,149600000,1,0,1,1083,12735
+Mars,227900000,2,0,2,163,6767
+Jupiter,778500000,53,26,79,1431280,142324
+Saturn,1434000900,53,29,81,827130,124832
+Uranus,2871000900,27,0,27,68330,51726
+Neptune,4495000900,14,0,14,62540,49243
diff --git a/planets_name.csv b/planets_name.csv
@@ -0,0 +1 @@
+Earth,Jupiter,Mars,Mercury,Neptune,Saturn,Uranus,Venus