Upload New File

Paddy_Waste.py

+import pandas as pd
+from sklearn import metrics
+from sklearn.model_selection import train_test_split
+from sklearn.tree import export_graphviz
+from six import StringIO
+import pydotplus
+from sklearn.tree import DecisionTreeClassifier
+
+dataset = pd.read_csv('FarmingData/DataCollected.csv')
+dataset.shape
+
+dataset['chemicalsType'].replace({'organic': 1}, inplace=True)
+tableData = dataset[(dataset["SeedType"] == 'Nadu')]
+
+dataset['WasteAmount'] = (dataset['wastage'] / 100) * dataset['production']
+
+tableData = dataset.head()
+print(tableData)
+
+# Preparing the Data
+feature_cols = ['Seeds', 'DailyWater', 'chemicalsType']
+
+X = dataset[['Seeds', 'DailyWater', 'chemicalsType']]
+y = dataset['WasteAmount']
+
+# Training and Making Predictions 0.80 tranning
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20)
+
+# set  DecisionTreeClassifier algorithm
+classifier = DecisionTreeClassifier()
+classifier.fit(X_train, y_train)
+y_pred = classifier.predict(X_test)
+
+dot_data = StringIO()
+export_graphviz(classifier, 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())
+
+# used Seeds Kg , DailyWater , chemicalsType Used
+new_input = [[18000,1000,2]]
+pred = classifier.predict(new_input)
+print(pred)
+
+# measure Accuracy
+print("Accuracy:",metrics.accuracy_score(y_test, y_pred) * 100 )
\ No newline at end of file