{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30558,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport tensorflow as tf\nfrom keras.datasets import mnist\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras import layers","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:03.907484Z","iopub.execute_input":"2023-10-08T16:54:03.908215Z","iopub.status.idle":"2023-10-08T16:54:15.175801Z","shell.execute_reply.started":"2023-10-08T16:54:03.908165Z","shell.execute_reply":"2023-10-08T16:54:15.173553Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:15.178359Z","iopub.execute_input":"2023-10-08T16:54:15.179109Z","iopub.status.idle":"2023-10-08T16:54:21.135348Z","shell.execute_reply.started":"2023-10-08T16:54:15.179071Z","shell.execute_reply":"2023-10-08T16:54:21.13401Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"data = mnist.load_data()","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:21.136915Z","iopub.execute_input":"2023-10-08T16:54:21.137268Z","iopub.status.idle":"2023-10-08T16:54:22.776379Z","shell.execute_reply.started":"2023-10-08T16:54:21.137238Z","shell.execute_reply":"2023-10-08T16:54:22.775017Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n11490434/11490434 [==============================] - 1s 0us/step\n","output_type":"stream"}]},{"cell_type":"code","source":"(xtrain, ytrain),(xtest, ytest) = data","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.777794Z","iopub.execute_input":"2023-10-08T16:54:22.77815Z","iopub.status.idle":"2023-10-08T16:54:22.783133Z","shell.execute_reply.started":"2023-10-08T16:54:22.778119Z","shell.execute_reply":"2023-10-08T16:54:22.782098Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"xtrain.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.786065Z","iopub.execute_input":"2023-10-08T16:54:22.786411Z","iopub.status.idle":"2023-10-08T16:54:22.803244Z","shell.execute_reply.started":"2023-10-08T16:54:22.786382Z","shell.execute_reply":"2023-10-08T16:54:22.801789Z"},"trusted":true},"execution_count":5,"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"(60000, 28, 28)"},"metadata":{}}]},{"cell_type":"code","source":"ytrain.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.805032Z","iopub.execute_input":"2023-10-08T16:54:22.805716Z","iopub.status.idle":"2023-10-08T16:54:22.81762Z","shell.execute_reply.started":"2023-10-08T16:54:22.805679Z","shell.execute_reply":"2023-10-08T16:54:22.816285Z"},"trusted":true},"execution_count":6,"outputs":[{"execution_count":6,"output_type":"execute_result","data":{"text/plain":"(60000,)"},"metadata":{}}]},{"cell_type":"code","source":"xtest.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.819117Z","iopub.execute_input":"2023-10-08T16:54:22.819444Z","iopub.status.idle":"2023-10-08T16:54:22.832625Z","shell.execute_reply.started":"2023-10-08T16:54:22.819417Z","shell.execute_reply":"2023-10-08T16:54:22.831283Z"},"trusted":true},"execution_count":7,"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"(10000, 28, 28)"},"metadata":{}}]},{"cell_type":"code","source":"ytest.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.834145Z","iopub.execute_input":"2023-10-08T16:54:22.834445Z","iopub.status.idle":"2023-10-08T16:54:22.849651Z","shell.execute_reply.started":"2023-10-08T16:54:22.834421Z","shell.execute_reply":"2023-10-08T16:54:22.848377Z"},"trusted":true},"execution_count":8,"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"(10000,)"},"metadata":{}}]},{"cell_type":"code","source":"test.shape","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.851031Z","iopub.execute_input":"2023-10-08T16:54:22.852179Z","iopub.status.idle":"2023-10-08T16:54:22.86299Z","shell.execute_reply.started":"2023-10-08T16:54:22.852142Z","shell.execute_reply":"2023-10-08T16:54:22.862004Z"},"trusted":true},"execution_count":9,"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"(28000, 784)"},"metadata":{}}]},{"cell_type":"code","source":"f,ax = plt.subplots(3,5, figsize=(25,15))\nfor i,ax in zip(range(15), ax.reshape(-1)):\n    ax.imshow(xtrain[i])\n    ax.set_title(ytrain[i])\n    ax.axis(False)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:22.86419Z","iopub.execute_input":"2023-10-08T16:54:22.864508Z","iopub.status.idle":"2023-10-08T16:54:24.130383Z","shell.execute_reply.started":"2023-10-08T16:54:22.864484Z","shell.execute_reply":"2023-10-08T16:54:24.129211Z"},"trusted":true},"execution_count":10,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 2500x1500 with 15 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"unique_labels, label_counts = np.unique(ytrain, return_counts=True)\n\nfor label, count in zip(unique_labels, label_counts):\n    print(f\"Label: {label}, Count: {count}\")","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.131845Z","iopub.execute_input":"2023-10-08T16:54:24.132487Z","iopub.status.idle":"2023-10-08T16:54:24.13918Z","shell.execute_reply.started":"2023-10-08T16:54:24.132452Z","shell.execute_reply":"2023-10-08T16:54:24.138008Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"Label: 0, Count: 5923\nLabel: 1, Count: 6742\nLabel: 2, Count: 5958\nLabel: 3, Count: 6131\nLabel: 4, Count: 5842\nLabel: 5, Count: 5421\nLabel: 6, Count: 5918\nLabel: 7, Count: 6265\nLabel: 8, Count: 5851\nLabel: 9, Count: 5949\n","output_type":"stream"}]},{"cell_type":"code","source":"xtrainr = xtrain.reshape(-1, 28, 28, 1)\nxtestr = xtest.reshape(-1, 28, 28, 1)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.140844Z","iopub.execute_input":"2023-10-08T16:54:24.1413Z","iopub.status.idle":"2023-10-08T16:54:24.152336Z","shell.execute_reply.started":"2023-10-08T16:54:24.141259Z","shell.execute_reply":"2023-10-08T16:54:24.15105Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"testr  = test.values.reshape(-1,28,28,1)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.153825Z","iopub.execute_input":"2023-10-08T16:54:24.154225Z","iopub.status.idle":"2023-10-08T16:54:24.16677Z","shell.execute_reply.started":"2023-10-08T16:54:24.154195Z","shell.execute_reply":"2023-10-08T16:54:24.165753Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"ytrainr = tf.keras.utils.to_categorical(ytrain, num_classes=10)\nytestr = tf.keras.utils.to_categorical(ytest, num_classes=10)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.172169Z","iopub.execute_input":"2023-10-08T16:54:24.1726Z","iopub.status.idle":"2023-10-08T16:54:24.185708Z","shell.execute_reply.started":"2023-10-08T16:54:24.172515Z","shell.execute_reply":"2023-10-08T16:54:24.184235Z"},"trusted":true},"execution_count":14,"outputs":[]},{"cell_type":"code","source":"resizing = tf.keras.models.Sequential([\n    layers.Resizing(28,28),\n    layers.Rescaling(1./255)\n])","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.187228Z","iopub.execute_input":"2023-10-08T16:54:24.187711Z","iopub.status.idle":"2023-10-08T16:54:24.304214Z","shell.execute_reply.started":"2023-10-08T16:54:24.187669Z","shell.execute_reply":"2023-10-08T16:54:24.303299Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"cnn = tf.keras.models.Sequential([\n    resizing\n])","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.305989Z","iopub.execute_input":"2023-10-08T16:54:24.306785Z","iopub.status.idle":"2023-10-08T16:54:24.317125Z","shell.execute_reply.started":"2023-10-08T16:54:24.306739Z","shell.execute_reply":"2023-10-08T16:54:24.315797Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"# Adding Convolutional and Pooling Layers\n\ncnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu'))\ncnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))\n\n# Adding more layers\n\ncnn.add(tf.keras.layers.Conv2D(filters=64, kernel_size=3, activation='relu', padding='same'))\ncnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2, padding='same'))\n\ncnn.add(tf.keras.layers.Conv2D(filters=128, kernel_size=3, activation='relu', padding='same'))\ncnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2, padding='same'))","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.318812Z","iopub.execute_input":"2023-10-08T16:54:24.320051Z","iopub.status.idle":"2023-10-08T16:54:24.346087Z","shell.execute_reply.started":"2023-10-08T16:54:24.320002Z","shell.execute_reply":"2023-10-08T16:54:24.344965Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"# Flattening layer\ncnn.add(tf.keras.layers.Flatten())","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.347472Z","iopub.execute_input":"2023-10-08T16:54:24.348636Z","iopub.status.idle":"2023-10-08T16:54:24.353967Z","shell.execute_reply.started":"2023-10-08T16:54:24.348562Z","shell.execute_reply":"2023-10-08T16:54:24.352939Z"},"trusted":true},"execution_count":18,"outputs":[]},{"cell_type":"code","source":"# Hidden Layer to train neural network\ncnn.add(tf.keras.layers.Dense(units=128, activation='relu'))\ncnn.add(tf.keras.layers.Dense(units=128, activation='relu'))\ncnn.add(tf.keras.layers.Dense(units=128, activation='relu'))\ncnn.add(tf.keras.layers.Dense(units=128, activation='relu'))","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.355303Z","iopub.execute_input":"2023-10-08T16:54:24.356466Z","iopub.status.idle":"2023-10-08T16:54:24.375752Z","shell.execute_reply.started":"2023-10-08T16:54:24.356433Z","shell.execute_reply":"2023-10-08T16:54:24.374624Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"code","source":"# Output Layer\ncnn.add(tf.keras.layers.Dense(units=10, activation='softmax'))","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.377485Z","iopub.execute_input":"2023-10-08T16:54:24.378622Z","iopub.status.idle":"2023-10-08T16:54:24.393636Z","shell.execute_reply.started":"2023-10-08T16:54:24.378554Z","shell.execute_reply":"2023-10-08T16:54:24.392772Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"# Compiling using Stochastic Gradient Descent and Loss function\ncnn.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.394997Z","iopub.execute_input":"2023-10-08T16:54:24.395606Z","iopub.status.idle":"2023-10-08T16:54:24.435442Z","shell.execute_reply.started":"2023-10-08T16:54:24.395554Z","shell.execute_reply":"2023-10-08T16:54:24.434664Z"},"trusted":true},"execution_count":21,"outputs":[]},{"cell_type":"code","source":"early_stopping_callback = EarlyStopping(monitor='val_loss',\n                                       patience=5,\n                                       mode='min',\n                                       verbose=1)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.436819Z","iopub.execute_input":"2023-10-08T16:54:24.437404Z","iopub.status.idle":"2023-10-08T16:54:24.443351Z","shell.execute_reply.started":"2023-10-08T16:54:24.43737Z","shell.execute_reply":"2023-10-08T16:54:24.441835Z"},"trusted":true},"execution_count":22,"outputs":[]},{"cell_type":"code","source":"# Train Neural Network\ncnn.fit(x=xtrainr, y= ytrainr, epochs=100, batch_size=32, validation_data=(xtestr, ytestr), callbacks=early_stopping_callback)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T16:54:24.444908Z","iopub.execute_input":"2023-10-08T16:54:24.44523Z","iopub.status.idle":"2023-10-08T17:05:56.784499Z","shell.execute_reply.started":"2023-10-08T16:54:24.445203Z","shell.execute_reply":"2023-10-08T17:05:56.782774Z"},"trusted":true},"execution_count":23,"outputs":[{"name":"stdout","text":"Epoch 1/100\n1875/1875 [==============================] - 66s 34ms/step - loss: 0.1579 - accuracy: 0.9493 - val_loss: 0.0473 - val_accuracy: 0.9858\nEpoch 2/100\n1875/1875 [==============================] - 65s 35ms/step - loss: 0.0528 - accuracy: 0.9848 - val_loss: 0.0452 - val_accuracy: 0.9866\nEpoch 3/100\n1875/1875 [==============================] - 63s 33ms/step - loss: 0.0367 - accuracy: 0.9898 - val_loss: 0.0317 - val_accuracy: 0.9901\nEpoch 4/100\n1875/1875 [==============================] - 61s 33ms/step - loss: 0.0332 - accuracy: 0.9906 - val_loss: 0.0370 - val_accuracy: 0.9898\nEpoch 5/100\n1875/1875 [==============================] - 60s 32ms/step - loss: 0.0253 - accuracy: 0.9930 - val_loss: 0.0315 - val_accuracy: 0.9910\nEpoch 6/100\n1875/1875 [==============================] - 62s 33ms/step - loss: 0.0224 - accuracy: 0.9941 - val_loss: 0.0270 - val_accuracy: 0.9926\nEpoch 7/100\n1875/1875 [==============================] - 66s 35ms/step - loss: 0.0201 - accuracy: 0.9948 - val_loss: 0.0402 - val_accuracy: 0.9885\nEpoch 8/100\n1875/1875 [==============================] - 64s 34ms/step - loss: 0.0184 - accuracy: 0.9952 - val_loss: 0.0399 - val_accuracy: 0.9899\nEpoch 9/100\n1875/1875 [==============================] - 60s 32ms/step - loss: 0.0142 - accuracy: 0.9961 - val_loss: 0.0417 - val_accuracy: 0.9893\nEpoch 10/100\n1875/1875 [==============================] - 62s 33ms/step - loss: 0.0150 - accuracy: 0.9956 - val_loss: 0.0425 - val_accuracy: 0.9914\nEpoch 11/100\n1875/1875 [==============================] - 64s 34ms/step - loss: 0.0164 - accuracy: 0.9957 - val_loss: 0.0288 - val_accuracy: 0.9932\nEpoch 11: early stopping\n","output_type":"stream"},{"execution_count":23,"output_type":"execute_result","data":{"text/plain":"<keras.callbacks.History at 0x7c4b30eefb80>"},"metadata":{}}]},{"cell_type":"code","source":"# Predict the Test data on neuron\nypred = cnn.predict(xtest)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:05:56.786229Z","iopub.execute_input":"2023-10-08T17:05:56.786732Z","iopub.status.idle":"2023-10-08T17:06:02.097815Z","shell.execute_reply.started":"2023-10-08T17:05:56.786686Z","shell.execute_reply":"2023-10-08T17:06:02.09639Z"},"trusted":true},"execution_count":24,"outputs":[{"name":"stdout","text":"313/313 [==============================] - 4s 11ms/step\n","output_type":"stream"}]},{"cell_type":"code","source":"# Using argmax() to return maximum values along an axis.\ntest_preds = []\nfor i in range(len(ypred)):\n    test_preds.append(np.argmax(ypred[i]))","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:02.100324Z","iopub.execute_input":"2023-10-08T17:06:02.101239Z","iopub.status.idle":"2023-10-08T17:06:02.137692Z","shell.execute_reply.started":"2023-10-08T17:06:02.101172Z","shell.execute_reply":"2023-10-08T17:06:02.136522Z"},"trusted":true},"execution_count":25,"outputs":[]},{"cell_type":"code","source":"f,ax = plt.subplots(3,5, figsize=(25,15))\nfor i,ax in zip(range(15), ax.reshape(-1)):\n    ax.imshow(xtest[i])\n    ax.set_title(f\"{test_preds[i]}, {ytest[i]}\")\n    ax.axis(False)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:02.138875Z","iopub.execute_input":"2023-10-08T17:06:02.13991Z","iopub.status.idle":"2023-10-08T17:06:03.502316Z","shell.execute_reply.started":"2023-10-08T17:06:02.139868Z","shell.execute_reply":"2023-10-08T17:06:03.500724Z"},"trusted":true},"execution_count":26,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 2500x1500 with 15 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"cnn.save('model_new.h5')","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:03.504091Z","iopub.execute_input":"2023-10-08T17:06:03.504428Z","iopub.status.idle":"2023-10-08T17:06:03.589266Z","shell.execute_reply.started":"2023-10-08T17:06:03.504401Z","shell.execute_reply":"2023-10-08T17:06:03.587912Z"},"trusted":true},"execution_count":27,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:03.590648Z","iopub.execute_input":"2023-10-08T17:06:03.590986Z","iopub.status.idle":"2023-10-08T17:06:03.612804Z","shell.execute_reply.started":"2023-10-08T17:06:03.59096Z","shell.execute_reply":"2023-10-08T17:06:03.611069Z"},"trusted":true},"execution_count":28,"outputs":[]},{"cell_type":"code","source":"# Predict the Test data on neuron\nypred1 = cnn.predict(testr)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:03.614304Z","iopub.execute_input":"2023-10-08T17:06:03.614716Z","iopub.status.idle":"2023-10-08T17:06:13.920978Z","shell.execute_reply.started":"2023-10-08T17:06:03.614683Z","shell.execute_reply":"2023-10-08T17:06:13.919387Z"},"trusted":true},"execution_count":29,"outputs":[{"name":"stdout","text":"875/875 [==============================] - 9s 11ms/step\n","output_type":"stream"}]},{"cell_type":"code","source":"# Using argmax() to return maximum values along an axis.\ntest_preds1 = []\nfor i in range(len(ypred1)):\n    test_preds1.append(np.argmax(ypred1[i]))","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:13.922819Z","iopub.execute_input":"2023-10-08T17:06:13.92331Z","iopub.status.idle":"2023-10-08T17:06:13.996175Z","shell.execute_reply.started":"2023-10-08T17:06:13.923264Z","shell.execute_reply":"2023-10-08T17:06:13.995142Z"},"trusted":true},"execution_count":30,"outputs":[]},{"cell_type":"code","source":"f,ax = plt.subplots(3,5, figsize=(25,15))\nfor i,ax in zip(range(15), ax.reshape(-1)):\n    ax.imshow(testr[i])\n    ax.set_title(f\"{test_preds1[i]}\")\n    ax.axis(False)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:13.997554Z","iopub.execute_input":"2023-10-08T17:06:13.998559Z","iopub.status.idle":"2023-10-08T17:06:15.317971Z","shell.execute_reply.started":"2023-10-08T17:06:13.998511Z","shell.execute_reply":"2023-10-08T17:06:15.3167Z"},"trusted":true},"execution_count":31,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 2500x1500 with 15 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"sub.Label = test_preds1\nsub.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-10-08T17:06:15.319958Z","iopub.execute_input":"2023-10-08T17:06:15.321213Z","iopub.status.idle":"2023-10-08T17:06:15.447513Z","shell.execute_reply.started":"2023-10-08T17:06:15.321171Z","shell.execute_reply":"2023-10-08T17:06:15.446061Z"},"trusted":true},"execution_count":32,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}