Merge branch 'IT18523256_GunarathnaK.A.G.I.P.T' into 'master'

Adding new Python modules and SVm

See merge request !20

.idea/csv-plugin.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="CsvFileAttributes">
+    <option name="attributeMap">
+      <map>
+        <entry key="\diet_plan\weight_data.csv">
+          <value>
+            <Attribute>
+              <option name="separator" value="," />
+            </Attribute>
+          </value>
+        </entry>
+      </map>
+    </option>
+  </component>
+</project>
\ No newline at end of file

diet_plan/API.py

+import numpy
+from flask import Flask
+from flask import request
+from flask_cors import CORS
+from sklearn import preprocessing
+import pandas as pd
+
+le = preprocessing.LabelEncoder()
+
+dataDf = pd.read_csv("weight_data_with_headers.csv")
+le.fit(dataDf['breed'])
+dataDf['breed'] = le.transform(dataDf['breed'])
+
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+
+X = dataDf[['breed', 'height', 'weight']]
+y = dataDf['outcome']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
+
+from sklearn.svm import SVC
+clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
+clf.fit(X, y)
+
+app = Flask(__name__)
+cors = CORS(app)
+
+@app.route("/predict", methods =['POST'])
+def predict():
+    data = numpy.array(request.get_json())
+    print(data)
+    prediction = clf.predict(data)
+    print(prediction)
+    return {"pred": str(prediction[0])}
+
+if __name__ == '__main__':
+    app.run(debug=True, port=5003, host="0.0.0.0")

diet_plan/API_puppy.py

+import numpy
+from flask import Flask
+from flask import request
+from flask_cors import CORS
+from sklearn import preprocessing
+import pandas as pd
+
+le = preprocessing.LabelEncoder()
+
+dataDf = pd.read_csv("weight_data_with_headers_puppy.csv")
+le.fit(dataDf['breed'])
+dataDf['breed'] = le.transform(dataDf['breed'])
+
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+
+X = dataDf[['breed', 'month', 'weight']]
+y = dataDf['outcome']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
+
+from sklearn.svm import SVC
+clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
+clf.fit(X, y)
+
+app = Flask(__name__)
+cors = CORS(app)
+
+@app.route("/predict", methods =['POST'])
+def predict():
+    data = numpy.array(request.get_json())
+    print(data)
+    prediction = clf.predict(data)
+    print(prediction)
+    return {"pred": str(prediction[0])}
+
+if __name__ == '__main__':
+    app.run(debug=True, port=5004, host="0.0.0.0")

diet_plan/confusion matrix SVM.txt

+[[159  15   1]
+ [ 35 137  26]
+ [  0  14 155]]
\ No newline at end of file

diet_plan/confusion matrix logistic regression.txt

+[[124  46   5]
+ [ 66  79  53]
+ [ 24  47  98]]
\ No newline at end of file

diet_plan/data_analysis_and_models.py

+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn import preprocessing
+
+le = preprocessing.LabelEncoder()
+
+sns.set_style("whitegrid")
+plt.style.use("fivethirtyeight")
+
+dataDf = pd.read_csv("weight_data_with_headers.csv")
+le.fit(dataDf['breed'])
+print(le.classes_)
+dataDf['breed'] = le.transform(dataDf['breed'])
+
+print(dataDf.head())
+
+sns.pairplot(dataDf)
+plt.show()
+sns.heatmap(dataDf.corr(), annot=True)
+plt.show()
+
+corr = dataDf.corr(method='pearson')
+print(corr)
+
+from sklearn.model_selection import train_test_split
+
+X = dataDf[['breed', 'height', 'weight']]
+y = dataDf['outcome']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
+
+from sklearn.linear_model import LogisticRegression
+
+# LOGISTIC REGRESSION
+clf = LogisticRegression(random_state=0, max_iter=2000, solver='lbfgs').fit(X_train, y_train)
+predictions = clf.predict(X_test)
+score = clf.score(X_test, y_test)
+print("Logistic regression score: ", score)
+
+from sklearn import metrics
+cm = metrics.confusion_matrix(y_test, predictions)
+print(cm)
+
+plt.figure(figsize=(9,9))
+sns.heatmap(cm, annot=True, fmt=".3f", linewidths=.5, square = True, cmap = 'Blues_r');
+plt.ylabel('Actual label');
+plt.xlabel('Predicted label');
+all_sample_title = 'Accuracy Score: {0}'.format(score)
+plt.title(all_sample_title, size = 15)
+plt.show()
+
+# SVM
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+
+from sklearn.svm import SVC
+clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
+clf.fit(X, y)
+score = clf.score(X, y, sample_weight=None)
+print("SVM score: ", score)
+predictions = clf.predict(X_test)
+cm = metrics.confusion_matrix(y_test, predictions)
+print(cm)
+
+plt.figure(figsize=(9,9))
+sns.heatmap(cm, annot=True, fmt=".3f", linewidths=.5, square = True, cmap = 'Blues_r');
+plt.ylabel('Actual label');
+plt.xlabel('Predicted label');
+all_sample_title = 'Accuracy Score: {0}'.format(score)
+plt.title(all_sample_title, size = 15)
+plt.show()

diet_plan/logistic_regression_weight.py

 #import pandas
 import pandas as pd
-
-#creating columns for dataset preview
 col_names = ['breed', 'age', 'weight', 'label']
-dog_breeds = ["german_sheppard", "labrador", "pomeranian", "husky", "golden_retriever", "poodle", "bulldog", "shiba", "rottweiler","boxer","Dobermen"]
-
-# reading data set
+dog_breeds = ["german_sheppard", "labrador", "pomeranian", "husky", "golden_retriever", "poodle", "bulldog", "shiba", "rottweiler"]
+# load dataset
 pima = pd.read_csv("weight_data.csv", header=None, names=col_names)
 print("===================")
 print("Dataset head")
 print("===================")
-#previewing the head of data set
 print(pima.head())
 
-#split dataset in to features and target variable
+
+#split dataset in features and target variable
 feature_cols = ['breed', 'age', 'weight']
 X = pima[feature_cols] # Features
 y = pima.label # Target variable
 
-#Use sklearn to train dataset
 from sklearn.model_selection import train_test_split
 X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)
 
 # import the class
-#use logistic Regression
 from sklearn.linear_model import LogisticRegression
 
 # instantiate the model (using the default parameters)
@@ -32,6 +27,7 @@ logreg = LogisticRegression()
 # fit the model with data
 logreg.fit(X_train,y_train)
 
+#
 y_pred=logreg.predict(X_test)
 
 # import the metrics class
@@ -40,18 +36,16 @@ cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
 print("===================")
 print("Confusion matrix")
 print("===================")
-#printing a confusion matrix
 print(cnf_matrix)
 
 print("===================")
 print("Accuracy")
 print("===================")
-#printing the accuracy of model
 print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
 # print("Precision:",metrics.precision_score(y_test, y_pred))
 # print("Recall:",metrics.recall_score(y_test, y_pred))
 
 # Prediction test
-y_prediction_test = logreg.predict([[5,4,22]])
+y_prediction_test = logreg.predict([[1,1,3]])
 y_labels = ["Overweight", "Normal", "Underweight"]
 print(y_labels[y_prediction_test[0]])