From 7b863a88f3d136a4beb943ce8011c805c1eebfe3 Mon Sep 17 00:00:00 2001
From: Wojciech Lidwin <59863785+Halal37@users.noreply.github.com>
Date: Thu, 11 May 2023 17:47:16 +0200
Subject: [PATCH] 5_python_scripts

---
 ium_predict.py | 46 +++++++++++++++++++++++++++++++++++++++++
 ium_train.py   | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)
 create mode 100644 ium_predict.py
 create mode 100644 ium_train.py

diff --git a/ium_predict.py b/ium_predict.py
new file mode 100644
index 0000000..2c91ead
--- /dev/null
+++ b/ium_predict.py
@@ -0,0 +1,46 @@
+from keras.models import Sequential, load_model
+import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+from sklearn import metrics
+import math
+import numpy as np
+
+
+def write_list(names):
+    with open('listfile.txt', 'w') as fp:
+        fp.write("\n".join(str(item) for item in names))
+
+def get_x_y(data):
+    lb = LabelEncoder()
+
+    data = data.drop(["Location 1"], axis=1)
+    data = data.drop(columns=["Longitude", "Latitude", "Location", "Total Incidents", "CrimeTime", "Neighborhood", "Post", "CrimeDate", "Inside/Outside"], axis=1)
+    for column_name in data.columns:
+        data[column_name] = lb.fit_transform(data[column_name])
+    x = data.drop('Weapon', axis=1)
+    y = data['Weapon']
+
+
+
+    return data, x, y
+
+
+def predict():
+    model = load_model('baltimore_model3')
+
+    train = pd.read_csv('baltimore_train.csv')
+    baltimore_data_test = pd.read_csv('baltimore_test.csv')
+    baltimore_data_test.columns = train.columns
+    baltimore_data_test, x_test, y_test = get_x_y(baltimore_data_test)
+    scores = model.evaluate(x_test, y_test)
+    print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1] * 100))
+
+    y_predicted = model.predict(x_test)
+    y_predicted = np.argmax(y_predicted,axis=1)
+    test_results = {}
+    test_results['Weapon'] = model.evaluate(
+        x_test,
+        y_test, verbose=0)
+    write_list(y_predicted)
+
+predict()
\ No newline at end of file
diff --git a/ium_train.py b/ium_train.py
new file mode 100644
index 0000000..9b20fe2
--- /dev/null
+++ b/ium_train.py
@@ -0,0 +1,55 @@
+# This is a sample Python script.
+
+# Press Shift+F10 to execute it or replace it with your code.
+# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
+from keras.models import Sequential, load_model
+from keras.layers import Dense, Dropout
+from keras.optimizers import Adam
+import pandas as pd
+import tensorflow as tf
+import numpy as np
+from sklearn.preprocessing import LabelEncoder
+
+
+def get_x_y(data):
+
+    lb = LabelEncoder()
+    data = data.drop(["Location 1"], axis=1)
+    data = data.drop(columns=["Longitude", "Latitude", "Location", "Total Incidents", "CrimeTime", "Neighborhood", "Post", "CrimeDate", "Inside/Outside"], axis=1)
+    for column_name in data.columns:
+        data[column_name] = lb.fit_transform(data[column_name])
+    x = data.drop('Weapon', axis=1)
+    y = data['Weapon']
+
+
+
+    return data, x, y
+
+
+def train_model():
+    train = pd.read_csv('baltimore_train.csv')
+
+    data_train, x_train, y_train = get_x_y(train)
+    normalizer = tf.keras.layers.Normalization(axis=1)
+    normalizer.adapt(np.array(x_train))
+    model = Sequential(normalizer)
+    model.add(Dense(64, activation="relu"))
+    model.add(Dense(10, activation='relu'))
+    model.add(Dense(10, activation='relu'))
+    model.add(Dense(10, activation='relu'))
+    model.add(Dense(5, activation="softmax"))
+    model.compile(Adam(learning_rate=0.01), loss='sparse_categorical_crossentropy', metrics = ['accuracy'] )
+    model.summary()
+
+    history = model.fit(
+        x_train,
+        y_train,
+        epochs=20,
+        validation_split=0.2)
+    hist = pd.DataFrame(history.history)
+    hist['epoch'] = history.epoch
+    model.save('baltimore_model3')
+
+
+train_model()
+