Create app.py

app.py

@@ -0,0 +1,190 @@
+import warnings
+warnings.filterwarnings('ignore')
+import pandas as pd
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import precision_score
+from sklearn.metrics import recall_score
+from sklearn.metrics import f1_score
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.utils import shuffle
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import classification_report, confusion_matrix
+from sklearn.model_selection import StratifiedKFold
+from sklearn import svm
+import numpy as np
+from sklearn.inspection import permutation_importance
+import gradio as gr
+
+df = pd.read_csv('flies.csv')
+
+replacement = {
+    'a': 0,
+    'x': 1
+}
+
+df['Type'] = df['Type'].map(replacement)
+
+cols_to_use = ['Wing Length (cm)', 'Abdomen Length (cm)', 'Antenna Length (cm)', 'Max Antenna Width (cm)']
+# cols_to_use = ['Abdomen Length (cm)']
+
+df_use = df[[*cols_to_use, 'Type']]
+
+# Shuffle the dataframe
+df_use = shuffle(df_use)
+x = df_use.iloc[:,0:len(df_use.columns)-1]
+y = df_use.iloc[:, -1]
+features = x.columns.values
+scaler = MinMaxScaler(feature_range = (0,1))
+scaler.fit(x)
+x = pd.DataFrame(scaler.transform(x))
+x.columns = features
+# x_train ,x_test , y_train ,y_test = train_test_split(x, y, train_size= 0.8)
+# print(x)
+
+skf = StratifiedKFold(n_splits=4, shuffle=True)
+kfold = skf.split(x, y)
+
+confusions = []
+accs = []
+precisions = []
+recalls = []
+f1s = []
+importances = []
+for i, x in enumerate(kfold):
+    print(f"\n------------------Fold: {i+1}---------------")
+
+    train, test = df_use.iloc[x[0].tolist()], df_use.iloc[x[1].tolist()]
+    ytrain = train[["Type"]]
+    print(f"Training: {len(train)}")
+    print(f"Testing: {len(test)}")
+    ytest = test[["Type"]]
+
+    xtrain = train.drop("Type", axis=1)
+    xtest = test.drop("Type", axis=1)
+
+    model = svm.SVC(kernel='poly')
+    model.fit(xtrain , np.squeeze(ytrain))
+    ypred = model.predict(xtest)
+
+
+    confusions.append(confusion_matrix(ytest, ypred))
+    accs.append(accuracy_score(ytest, ypred))
+    precisions.append(precision_score(ytest, ypred))
+    recalls.append(recall_score(ytest, ypred))
+    f1s.append(f1_score(ytest, ypred))
+
+    
+
+    perm_importance = permutation_importance(model, xtest, ytest)
+    features = np.array(cols_to_use)
+
+    sorted_idx = perm_importance.importances_mean.argsort()
+
+    # print(perm_importance.importances_mean[sorted_idx])
+    importances.append(perm_importance.importances_mean[sorted_idx])
+
+
+avg_acc = sum(accs) / len(accs)
+avg_precision = sum(precisions) / len(precisions)
+avg_recall = sum(recalls) / len(recalls)
+avg_f1 = sum(f1s) / len(f1s)
+
+print()
+print
+print("Accuracy:", avg_acc)
+print("Precision:", avg_precision)
+print("Recall:", avg_recall)
+print("F1:", avg_f1)
+
+matrix = np.asmatrix(np.array(importances))
+# print(matrix)
+means = matrix.mean(0).A1 # convert back to array
+
+
+test1 = [2.81, 1.80, 1.24, 0.46]
+test2 = [2.65, 1.84, 1.28, 0.39]
+test3 = [3.61, 2.04, 1.40, 0.50]
+
+matrix = [
+    test1, test2, test3
+]
+
+
+
+wingL = []
+abdL = []
+antL = []
+antM = []
+
+for row in matrix:
+    wingL.append(row[0])
+    abdL.append(row[1])
+    antL.append(row[2])
+    antM.append(row[3])
+
+
+user_df = pd.DataFrame({
+    'Wing Length (cm)': wingL,
+    'Abdomen Length (cm)': abdL,
+    'Antenna Length (cm)': antL,
+     'Max Antenna Width (cm)': antM
+})
+
+user_df = scaler.transform(user_df)
+
+preds = model.predict(user_df)
+
+for pred in preds:
+  if pred == 0:
+    print("A", end = " ")
+  else:
+    print("X", end = " ")
+
+
+def main(wingL, abdL, antL, maxAW):
+    test1 = [2.81, 1.80, 1.24, 0.46]
+
+    matrix = [
+        test1
+    ]
+
+    wingL = []
+    abdL = []
+    antL = []
+    antM = []
+
+    for row in matrix:
+        wingL.append(row[0])
+        abdL.append(row[1])
+        antL.append(row[2])
+        antM.append(row[3])
+
+
+    user_df = pd.DataFrame({
+        'Wing Length (cm)': wingL,
+        'Abdomen Length (cm)': abdL,
+        'Antenna Length (cm)': antL,
+        'Max Antenna Width (cm)': antM
+    })
+
+    user_df = scaler.transform(user_df)
+
+    preds = model.predict(user_df)
+
+    if pred == 0:
+        return "A"
+    else:
+        return "X"
+
+gr.Interface(
+  fn=main, 
+  title="FlyCatcher",
+  inputs=[gr.inputs.Number(label="Wing Length (cm)"), 
+          gr.inputs.Number(label="Abdomen Length (cm)"),
+          gr.inputs.Number(label="Antenna Length (cm)"),
+          gr.inputs.Number(label="Max Antenna Width (cm)"),
+  ],
+  outputs=["text"],
+  theme="huggingface").launch(share=True)