{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30646,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-02-25T06:06:44.162338Z","iopub.execute_input":"2024-02-25T06:06:44.162654Z","iopub.status.idle":"2024-02-25T06:06:45.295652Z","shell.execute_reply.started":"2024-02-25T06:06:44.162626Z","shell.execute_reply":"2024-02-25T06:06:45.294521Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/digit-recognizer/sample_submission.csv\n/kaggle/input/digit-recognizer/train.csv\n/kaggle/input/digit-recognizer/test.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"pip install dashboard","metadata":{"execution":{"iopub.status.busy":"2024-02-26T11:21:32.224897Z","iopub.execute_input":"2024-02-26T11:21:32.225278Z","iopub.status.idle":"2024-02-26T11:21:53.068954Z","shell.execute_reply.started":"2024-02-26T11:21:32.225246Z","shell.execute_reply":"2024-02-26T11:21:53.067883Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Collecting dashboard\n Downloading dashboard-0.0.6-py3-none-any.whl (201 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m201.1/201.1 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hRequirement already satisfied: aiofiles in /opt/conda/lib/python3.10/site-packages (from dashboard) (22.1.0)\nRequirement already satisfied: starlette in /opt/conda/lib/python3.10/site-packages (from dashboard) (0.32.0.post1)\nRequirement already satisfied: uvicorn in /opt/conda/lib/python3.10/site-packages (from dashboard) (0.25.0)\nRequirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from dashboard) (3.1.2)\nCollecting python-multipart (from dashboard)\n Downloading python_multipart-0.0.9-py3-none-any.whl.metadata (2.5 kB)\nCollecting orm==0.2.0.dev1 (from dashboard)\n Downloading orm-0.2.0.dev1.tar.gz (9.8 kB)\n Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hCollecting typesystem==0.3.0.dev0 (from dashboard)\n Downloading typesystem-0.3.0.dev0.tar.gz (21 kB)\n Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hCollecting databases[sqlite] (from dashboard)\n Downloading databases-0.8.0-py3-none-any.whl.metadata (5.4 kB)\nCollecting sqlalchemy<1.5,>=1.4.42 (from databases[sqlite]->dashboard)\n Downloading SQLAlchemy-1.4.51-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (10 kB)\nRequirement already satisfied: aiosqlite in /opt/conda/lib/python3.10/site-packages (from databases[sqlite]->dashboard) (0.19.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->dashboard) (2.1.3)\nRequirement already satisfied: anyio<5,>=3.4.0 in /opt/conda/lib/python3.10/site-packages (from starlette->dashboard) (4.2.0)\nRequirement already satisfied: click>=7.0 in /opt/conda/lib/python3.10/site-packages (from uvicorn->dashboard) (8.1.7)\nRequirement already satisfied: h11>=0.8 in /opt/conda/lib/python3.10/site-packages (from uvicorn->dashboard) (0.14.0)\nRequirement already satisfied: typing-extensions>=4.0 in /opt/conda/lib/python3.10/site-packages (from uvicorn->dashboard) (4.9.0)\nRequirement already satisfied: idna>=2.8 in /opt/conda/lib/python3.10/site-packages (from anyio<5,>=3.4.0->starlette->dashboard) (3.6)\nRequirement already satisfied: sniffio>=1.1 in /opt/conda/lib/python3.10/site-packages (from anyio<5,>=3.4.0->starlette->dashboard) (1.3.0)\nRequirement already satisfied: exceptiongroup>=1.0.2 in /opt/conda/lib/python3.10/site-packages (from anyio<5,>=3.4.0->starlette->dashboard) (1.2.0)\nRequirement already satisfied: greenlet!=0.4.17 in /opt/conda/lib/python3.10/site-packages (from sqlalchemy<1.5,>=1.4.42->databases[sqlite]->dashboard) (3.0.3)\nDownloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\nDownloading databases-0.8.0-py3-none-any.whl (22 kB)\nDownloading SQLAlchemy-1.4.51-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m60.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hBuilding wheels for collected packages: orm, typesystem\n Building wheel for orm (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for orm: filename=orm-0.2.0.dev1-py3-none-any.whl size=10285 sha256=60065a34aa542ade75ec043a9378200ce1eaa12e403e52372f224f8459c91776\n Stored in directory: /root/.cache/pip/wheels/d2/69/bf/0d5a1ec253e6cc5d36647096f737a076f8a44627b72638f707\n Building wheel for typesystem (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for typesystem: filename=typesystem-0.3.0.dev0-py3-none-any.whl size=25038 sha256=eb940f2f5e6982aa623f8478b04ea42b8c9e8268a49d2b95f6668068037b6c1c\n Stored in directory: /root/.cache/pip/wheels/6e/0c/e2/021738a6eb9ffd82e69ef5d7a867337c104b831417313f4c33\nSuccessfully built orm typesystem\nInstalling collected packages: typesystem, sqlalchemy, python-multipart, databases, orm, dashboard\n Attempting uninstall: sqlalchemy\n Found existing installation: SQLAlchemy 2.0.25\n Uninstalling SQLAlchemy-2.0.25:\n Successfully uninstalled SQLAlchemy-2.0.25\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nipython-sql 0.5.0 requires sqlalchemy>=2.0, but you have sqlalchemy 1.4.51 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed dashboard-0.0.6 databases-0.8.0 orm-0.2.0.dev1 python-multipart-0.0.9 sqlalchemy-1.4.51 typesystem-0.3.0.dev0\nNote: you may need to restart the kernel to use updated packages.\n","output_type":"stream"}]},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:06:45.297781Z","iopub.execute_input":"2024-02-25T06:06:45.298313Z","iopub.status.idle":"2024-02-25T06:06:49.200093Z","shell.execute_reply.started":"2024-02-25T06:06:45.298275Z","shell.execute_reply":"2024-02-25T06:06:49.199016Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:06:49.20132Z","iopub.execute_input":"2024-02-25T06:06:49.201676Z","iopub.status.idle":"2024-02-25T06:06:49.228251Z","shell.execute_reply.started":"2024-02-25T06:06:49.201643Z","shell.execute_reply":"2024-02-25T06:06:49.227254Z"},"trusted":true},"execution_count":3,"outputs":[{"execution_count":3,"output_type":"execute_result","data":{"text/plain":" label pixel0 pixel1 pixel2 pixel3 pixel4 pixel5 pixel6 pixel7 \\\n0 1 0 0 0 0 0 0 0 0 \n1 0 0 0 0 0 0 0 0 0 \n2 1 0 0 0 0 0 0 0 0 \n3 4 0 0 0 0 0 0 0 0 \n4 0 0 0 0 0 0 0 0 0 \n\n pixel8 ... pixel774 pixel775 pixel776 pixel777 pixel778 pixel779 \\\n0 0 ... 0 0 0 0 0 0 \n1 0 ... 0 0 0 0 0 0 \n2 0 ... 0 0 0 0 0 0 \n3 0 ... 0 0 0 0 0 0 \n4 0 ... 0 0 0 0 0 0 \n\n pixel780 pixel781 pixel782 pixel783 \n0 0 0 0 0 \n1 0 0 0 0 \n2 0 0 0 0 \n3 0 0 0 0 \n4 0 0 0 0 \n\n[5 rows x 785 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
labelpixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8...pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
01000000000...0000000000
10000000000...0000000000
21000000000...0000000000
34000000000...0000000000
40000000000...0000000000
\n

5 rows × 785 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:06:49.231321Z","iopub.execute_input":"2024-02-25T06:06:49.231627Z","iopub.status.idle":"2024-02-25T06:06:49.237582Z","shell.execute_reply.started":"2024-02-25T06:06:49.231603Z","shell.execute_reply":"2024-02-25T06:06:49.236537Z"},"trusted":true},"execution_count":4,"outputs":[{"execution_count":4,"output_type":"execute_result","data":{"text/plain":"(42000, 785)"},"metadata":{}}]},{"cell_type":"code","source":"df.sample()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:12.508476Z","iopub.execute_input":"2024-02-25T06:07:12.509281Z","iopub.status.idle":"2024-02-25T06:07:12.534275Z","shell.execute_reply.started":"2024-02-25T06:07:12.509248Z","shell.execute_reply":"2024-02-25T06:07:12.53294Z"},"trusted":true},"execution_count":5,"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":" label pixel0 pixel1 pixel2 pixel3 pixel4 pixel5 pixel6 pixel7 \\\n39959 0 0 0 0 0 0 0 0 0 \n\n pixel8 ... pixel774 pixel775 pixel776 pixel777 pixel778 \\\n39959 0 ... 0 0 0 0 0 \n\n pixel779 pixel780 pixel781 pixel782 pixel783 \n39959 0 0 0 0 0 \n\n[1 rows x 785 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
labelpixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8...pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
399590000000000...0000000000
\n

1 rows × 785 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:13.38579Z","iopub.execute_input":"2024-02-25T06:07:13.386688Z","iopub.status.idle":"2024-02-25T06:07:13.390624Z","shell.execute_reply.started":"2024-02-25T06:07:13.386644Z","shell.execute_reply":"2024-02-25T06:07:13.389636Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"plt.imshow(df.iloc[41081,1:].values.reshape(28,28))","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:14.32442Z","iopub.execute_input":"2024-02-25T06:07:14.32507Z","iopub.status.idle":"2024-02-25T06:07:14.54425Z","shell.execute_reply.started":"2024-02-25T06:07:14.325038Z","shell.execute_reply":"2024-02-25T06:07:14.543314Z"},"trusted":true},"execution_count":7,"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"x = df.iloc[:,1:]\ny = df.iloc[:,0]","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:17.48288Z","iopub.execute_input":"2024-02-25T06:07:17.483681Z","iopub.status.idle":"2024-02-25T06:07:17.488295Z","shell.execute_reply.started":"2024-02-25T06:07:17.483648Z","shell.execute_reply":"2024-02-25T06:07:17.487202Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=42)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:19.883575Z","iopub.execute_input":"2024-02-25T06:07:19.884027Z","iopub.status.idle":"2024-02-25T06:07:20.622433Z","shell.execute_reply.started":"2024-02-25T06:07:19.883996Z","shell.execute_reply":"2024-02-25T06:07:20.621245Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"x_train.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:23.355282Z","iopub.execute_input":"2024-02-25T06:07:23.356191Z","iopub.status.idle":"2024-02-25T06:07:23.363622Z","shell.execute_reply.started":"2024-02-25T06:07:23.356156Z","shell.execute_reply":"2024-02-25T06:07:23.36277Z"},"trusted":true},"execution_count":10,"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"(33600, 784)"},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:26.849351Z","iopub.execute_input":"2024-02-25T06:07:26.849681Z","iopub.status.idle":"2024-02-25T06:07:27.059354Z","shell.execute_reply.started":"2024-02-25T06:07:26.849656Z","shell.execute_reply":"2024-02-25T06:07:27.058457Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"knn = KNeighborsClassifier()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:28.201409Z","iopub.execute_input":"2024-02-25T06:07:28.20175Z","iopub.status.idle":"2024-02-25T06:07:28.206022Z","shell.execute_reply.started":"2024-02-25T06:07:28.201724Z","shell.execute_reply":"2024-02-25T06:07:28.204998Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"knn.fit(x_train,y_train)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:29.90302Z","iopub.execute_input":"2024-02-25T06:07:29.903395Z","iopub.status.idle":"2024-02-25T06:07:30.027479Z","shell.execute_reply.started":"2024-02-25T06:07:29.903369Z","shell.execute_reply":"2024-02-25T06:07:30.026503Z"},"trusted":true},"execution_count":13,"outputs":[{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"KNeighborsClassifier()","text/html":"
KNeighborsClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
"},"metadata":{}}]},{"cell_type":"code","source":"import time \nstart = time.time()\ny_pred = knn.predict(x_test)\nprint(time.time()-start)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:32.137549Z","iopub.execute_input":"2024-02-25T06:07:32.137913Z","iopub.status.idle":"2024-02-25T06:07:41.744728Z","shell.execute_reply.started":"2024-02-25T06:07:32.137884Z","shell.execute_reply":"2024-02-25T06:07:41.743722Z"},"trusted":true},"execution_count":14,"outputs":[{"name":"stdout","text":"9.602374792098999\n","output_type":"stream"}]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\naccuracy_score(y_test,y_pred)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:41.746492Z","iopub.execute_input":"2024-02-25T06:07:41.746761Z","iopub.status.idle":"2024-02-25T06:07:41.754533Z","shell.execute_reply.started":"2024-02-25T06:07:41.746737Z","shell.execute_reply":"2024-02-25T06:07:41.753688Z"},"trusted":true},"execution_count":15,"outputs":[{"execution_count":15,"output_type":"execute_result","data":{"text/plain":"0.9648809523809524"},"metadata":{}}]},{"cell_type":"markdown","source":"With PCA :","metadata":{}},{"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\nscaler = StandardScaler()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:41.755713Z","iopub.execute_input":"2024-02-25T06:07:41.756084Z","iopub.status.idle":"2024-02-25T06:07:41.763771Z","shell.execute_reply.started":"2024-02-25T06:07:41.756051Z","shell.execute_reply":"2024-02-25T06:07:41.762858Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"# Data Mean Centered\nx_train = scaler.fit_transform(x_train)\nx_test = scaler.transform(x_test)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:41.765887Z","iopub.execute_input":"2024-02-25T06:07:41.766167Z","iopub.status.idle":"2024-02-25T06:07:42.227514Z","shell.execute_reply.started":"2024-02-25T06:07:41.766144Z","shell.execute_reply":"2024-02-25T06:07:42.226511Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"# PCA\nfrom sklearn.decomposition import PCA\npca = PCA(n_components=200)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:42.228583Z","iopub.execute_input":"2024-02-25T06:07:42.228878Z","iopub.status.idle":"2024-02-25T06:07:42.233681Z","shell.execute_reply.started":"2024-02-25T06:07:42.22885Z","shell.execute_reply":"2024-02-25T06:07:42.232754Z"},"trusted":true},"execution_count":18,"outputs":[]},{"cell_type":"code","source":"x_train_trf = pca.fit_transform(x_train)\nx_test_trf = pca.transform(x_test)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:43.278349Z","iopub.execute_input":"2024-02-25T06:07:43.279037Z","iopub.status.idle":"2024-02-25T06:07:46.534735Z","shell.execute_reply.started":"2024-02-25T06:07:43.279Z","shell.execute_reply":"2024-02-25T06:07:46.533102Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"code","source":"x_train_trf.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:46.536703Z","iopub.execute_input":"2024-02-25T06:07:46.540532Z","iopub.status.idle":"2024-02-25T06:07:46.548364Z","shell.execute_reply.started":"2024-02-25T06:07:46.540477Z","shell.execute_reply":"2024-02-25T06:07:46.547021Z"},"trusted":true},"execution_count":20,"outputs":[{"execution_count":20,"output_type":"execute_result","data":{"text/plain":"(33600, 200)"},"metadata":{}}]},{"cell_type":"code","source":"knn = KNeighborsClassifier()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:49.347397Z","iopub.execute_input":"2024-02-25T06:07:49.348086Z","iopub.status.idle":"2024-02-25T06:07:49.35213Z","shell.execute_reply.started":"2024-02-25T06:07:49.348054Z","shell.execute_reply":"2024-02-25T06:07:49.351189Z"},"trusted":true},"execution_count":21,"outputs":[]},{"cell_type":"code","source":"knn.fit(x_train_trf,y_train)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:52.468383Z","iopub.execute_input":"2024-02-25T06:07:52.469151Z","iopub.status.idle":"2024-02-25T06:07:52.501046Z","shell.execute_reply.started":"2024-02-25T06:07:52.469116Z","shell.execute_reply":"2024-02-25T06:07:52.500129Z"},"trusted":true},"execution_count":22,"outputs":[{"execution_count":22,"output_type":"execute_result","data":{"text/plain":"KNeighborsClassifier()","text/html":"
KNeighborsClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
"},"metadata":{}}]},{"cell_type":"code","source":"y_pred = knn.predict(x_test_trf)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:55.152999Z","iopub.execute_input":"2024-02-25T06:07:55.153372Z","iopub.status.idle":"2024-02-25T06:07:57.289876Z","shell.execute_reply.started":"2024-02-25T06:07:55.153342Z","shell.execute_reply":"2024-02-25T06:07:57.288868Z"},"trusted":true},"execution_count":23,"outputs":[]},{"cell_type":"code","source":"accuracy_score(y_test,y_pred)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:07:57.29144Z","iopub.execute_input":"2024-02-25T06:07:57.291735Z","iopub.status.idle":"2024-02-25T06:07:57.299891Z","shell.execute_reply.started":"2024-02-25T06:07:57.291712Z","shell.execute_reply":"2024-02-25T06:07:57.298801Z"},"trusted":true},"execution_count":24,"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":"0.9502380952380952"},"metadata":{}}]},{"cell_type":"code","source":"for i in range (1,100):\n pca = PCA( n_components=i)\n x_train_trf = pca.fit_transform(x_train)\n x_test_trf = pca.transform(x_test)\n \n knn = KNeighborsClassifier()\n \n knn.fit(x_train_trf,y_train)\n \n y_pred = knn.predict(x_test_trf)\n \n a=accuracy_score(y_test,y_pred)\n ","metadata":{"execution":{"iopub.status.busy":"2024-02-22T04:06:52.530397Z","iopub.execute_input":"2024-02-22T04:06:52.531218Z","iopub.status.idle":"2024-02-22T04:12:41.328921Z","shell.execute_reply.started":"2024-02-22T04:06:52.531186Z","shell.execute_reply":"2024-02-22T04:12:41.328079Z"},"trusted":true},"execution_count":26,"outputs":[]},{"cell_type":"code","source":"# Transform to a 2D coordinate system\npca = PCA(n_components=2)\nx_train_trf = pca.fit_transform(x_train)\nx_test_trf = pca.transform(x_test)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:02.539136Z","iopub.execute_input":"2024-02-25T06:08:02.539777Z","iopub.status.idle":"2024-02-25T06:08:03.698079Z","shell.execute_reply.started":"2024-02-25T06:08:02.539743Z","shell.execute_reply":"2024-02-25T06:08:03.696688Z"},"trusted":true},"execution_count":25,"outputs":[]},{"cell_type":"code","source":"x_train_trf","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:08.852682Z","iopub.execute_input":"2024-02-25T06:08:08.853597Z","iopub.status.idle":"2024-02-25T06:08:08.863434Z","shell.execute_reply.started":"2024-02-25T06:08:08.853563Z","shell.execute_reply":"2024-02-25T06:08:08.862511Z"},"trusted":true},"execution_count":26,"outputs":[{"execution_count":26,"output_type":"execute_result","data":{"text/plain":"array([[-2.71864293, -0.49049255],\n [-0.67701322, -6.75451229],\n [-3.03325782, 6.50913394],\n ...,\n [ 2.14880806, 0.78077166],\n [ 1.05957851, 0.94744 ],\n [17.70258378, 1.96145581]])"},"metadata":{}}]},{"cell_type":"code","source":"# Dynamic visualizations using plotly\nimport plotly.express as px\ny_train_trf = y_train.astype(str)\nfig = px.scatter(x=x_train_trf[:,0],\n y=x_train_trf[:,1],\n color=y_train_trf,\n color_discrete_sequence=px.colors.qualitative.G10\n )\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:10.418149Z","iopub.execute_input":"2024-02-25T06:08:10.41894Z","iopub.status.idle":"2024-02-25T06:08:12.825724Z","shell.execute_reply.started":"2024-02-25T06:08:10.418898Z","shell.execute_reply":"2024-02-25T06:08:12.824964Z"},"trusted":true},"execution_count":27,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/plotly/express/_core.py:2065: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.\n sf: grouped.get_group(s if len(s) > 1 else s[0])\n","output_type":"stream"},{"output_type":"display_data","data":{"text/html":" \n "},"metadata":{}},{"output_type":"display_data","data":{"text/html":"
"},"metadata":{}}]},{"cell_type":"code","source":"# Transforming in 3D\npca = PCA(n_components=3)\nx_train_trf = pca.fit_transform(x_train)\nx_test_trf = pca.transform(x_test)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:38.977958Z","iopub.execute_input":"2024-02-25T06:08:38.978592Z","iopub.status.idle":"2024-02-25T06:08:39.891752Z","shell.execute_reply.started":"2024-02-25T06:08:38.978555Z","shell.execute_reply":"2024-02-25T06:08:39.890292Z"},"trusted":true},"execution_count":28,"outputs":[]},{"cell_type":"code","source":"x_train_trf","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:41.62519Z","iopub.execute_input":"2024-02-25T06:08:41.625977Z","iopub.status.idle":"2024-02-25T06:08:41.632582Z","shell.execute_reply.started":"2024-02-25T06:08:41.625938Z","shell.execute_reply":"2024-02-25T06:08:41.631619Z"},"trusted":true},"execution_count":29,"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":"array([[-2.71865049, -0.48980184, 1.13514099],\n [-0.67697458, -6.75356966, -2.3358736 ],\n [-3.0332397 , 6.50974459, 7.49194011],\n ...,\n [ 2.14885793, 0.7806652 , -0.74719892],\n [ 1.05957184, 0.94760974, 3.94960589],\n [17.70258448, 1.96195671, -4.94371342]])"},"metadata":{}}]},{"cell_type":"code","source":"import plotly.express as px\ny_train_trf = y_train.astype(str)\nfig = px.scatter_3d(df, x=x_train_trf[:,0], y=x_train_trf[:,1], z=x_train_trf[:,2],\n color=y_train_trf)\nfig.update_layout(\n margin=dict(l=20, r=20, t=20, b=20),\n paper_bgcolor=\"LightSteelBlue\",\n)\nfig.show()\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:47.064184Z","iopub.execute_input":"2024-02-25T06:08:47.064541Z","iopub.status.idle":"2024-02-25T06:08:47.267763Z","shell.execute_reply.started":"2024-02-25T06:08:47.06451Z","shell.execute_reply":"2024-02-25T06:08:47.266844Z"},"trusted":true},"execution_count":30,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/plotly/express/_core.py:2065: FutureWarning:\n\nWhen grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.\n\n","output_type":"stream"},{"output_type":"display_data","data":{"text/html":"
"},"metadata":{}}]},{"cell_type":"code","source":"pca.explained_variance_\n# Eigen values","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:57.97515Z","iopub.execute_input":"2024-02-25T06:08:57.975502Z","iopub.status.idle":"2024-02-25T06:08:57.981626Z","shell.execute_reply.started":"2024-02-25T06:08:57.975473Z","shell.execute_reply":"2024-02-25T06:08:57.980658Z"},"trusted":true},"execution_count":31,"outputs":[{"execution_count":31,"output_type":"execute_result","data":{"text/plain":"array([40.67111198, 29.170234 , 26.7445961 ])"},"metadata":{}}]},{"cell_type":"code","source":"pca.components_.shape\n# Eigen vectors","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:08:59.6154Z","iopub.execute_input":"2024-02-25T06:08:59.615749Z","iopub.status.idle":"2024-02-25T06:08:59.621334Z","shell.execute_reply.started":"2024-02-25T06:08:59.615722Z","shell.execute_reply":"2024-02-25T06:08:59.620371Z"},"trusted":true},"execution_count":32,"outputs":[{"execution_count":32,"output_type":"execute_result","data":{"text/plain":"(3, 784)"},"metadata":{}}]},{"cell_type":"code","source":"pca.explained_variance_ratio_","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:01.047685Z","iopub.execute_input":"2024-02-25T06:09:01.048486Z","iopub.status.idle":"2024-02-25T06:09:01.054082Z","shell.execute_reply.started":"2024-02-25T06:09:01.048457Z","shell.execute_reply":"2024-02-25T06:09:01.053163Z"},"trusted":true},"execution_count":33,"outputs":[{"execution_count":33,"output_type":"execute_result","data":{"text/plain":"array([0.05785192, 0.0414927 , 0.03804239])"},"metadata":{}}]},{"cell_type":"code","source":"pca = PCA(n_components=None)\nX_train_trf = pca.fit_transform(x_train)\nX_test_trf = pca.transform(x_test)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:13.39353Z","iopub.execute_input":"2024-02-25T06:09:13.393919Z","iopub.status.idle":"2024-02-25T06:09:16.510667Z","shell.execute_reply.started":"2024-02-25T06:09:13.39389Z","shell.execute_reply":"2024-02-25T06:09:16.509064Z"},"trusted":true},"execution_count":35,"outputs":[]},{"cell_type":"code","source":"pca.explained_variance_.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:16.512907Z","iopub.execute_input":"2024-02-25T06:09:16.514049Z","iopub.status.idle":"2024-02-25T06:09:16.520934Z","shell.execute_reply.started":"2024-02-25T06:09:16.514002Z","shell.execute_reply":"2024-02-25T06:09:16.519871Z"},"trusted":true},"execution_count":36,"outputs":[{"execution_count":36,"output_type":"execute_result","data":{"text/plain":"(784,)"},"metadata":{}}]},{"cell_type":"code","source":"pca.components_.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:18.352746Z","iopub.execute_input":"2024-02-25T06:09:18.35351Z","iopub.status.idle":"2024-02-25T06:09:18.359695Z","shell.execute_reply.started":"2024-02-25T06:09:18.353472Z","shell.execute_reply":"2024-02-25T06:09:18.358676Z"},"trusted":true},"execution_count":37,"outputs":[{"execution_count":37,"output_type":"execute_result","data":{"text/plain":"(784, 784)"},"metadata":{}}]},{"cell_type":"code","source":"np.cumsum(pca.explained_variance_ratio_)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:19.90567Z","iopub.execute_input":"2024-02-25T06:09:19.906389Z","iopub.status.idle":"2024-02-25T06:09:19.92042Z","shell.execute_reply.started":"2024-02-25T06:09:19.906356Z","shell.execute_reply":"2024-02-25T06:09:19.919472Z"},"trusted":true},"execution_count":38,"outputs":[{"execution_count":38,"output_type":"execute_result","data":{"text/plain":"array([0.05785192, 0.09934462, 0.13738701, 0.16704964, 0.19286525,\n 0.21541506, 0.23514574, 0.25289854, 0.26858504, 0.28294568,\n 0.29664822, 0.30892077, 0.32038989, 0.33162017, 0.34220546,\n 0.35240477, 0.36198153, 0.37140862, 0.38053351, 0.38943521,\n 0.39783462, 0.40603525, 0.41388828, 0.42145568, 0.42882829,\n 0.43584714, 0.44282633, 0.44953738, 0.45593583, 0.4622392 ,\n 0.46839271, 0.4744166 , 0.48025334, 0.48603881, 0.49176214,\n 0.49722614, 0.50265822, 0.50793994, 0.51307376, 0.51801392,\n 0.52289063, 0.52771041, 0.53239246, 0.53698588, 0.54156249,\n 0.54605468, 0.5505015 , 0.55491691, 0.55926803, 0.56358836,\n 0.56780645, 0.57198888, 0.57606882, 0.58008887, 0.58407223,\n 0.58801822, 0.59188694, 0.59571889, 0.59948441, 0.60322635,\n 0.60687487, 0.6104829 , 0.61402176, 0.61750117, 0.62094441,\n 0.62432378, 0.62767368, 0.63099377, 0.63426257, 0.63746765,\n 0.64065542, 0.64376931, 0.64686564, 0.64992395, 0.65296104,\n 0.6559748 , 0.65895992, 0.66192105, 0.66483654, 0.66772536,\n 0.67060106, 0.6734651 , 0.67629295, 0.67910917, 0.68191711,\n 0.68468646, 0.68743018, 0.69013786, 0.69282727, 0.69548652,\n 0.6981275 , 0.70075516, 0.70335672, 0.7059274 , 0.70848658,\n 0.71103639, 0.71354984, 0.71605747, 0.71852606, 0.72096777,\n 0.72336938, 0.72575703, 0.72811046, 0.73043803, 0.73274819,\n 0.73504902, 0.73730548, 0.73955195, 0.74179168, 0.7440142 ,\n 0.74620053, 0.7483705 , 0.75051238, 0.7526383 , 0.75471786,\n 0.75677534, 0.758826 , 0.76083529, 0.76283446, 0.76482579,\n 0.76678392, 0.76873756, 0.77066405, 0.77258 , 0.77447592,\n 0.77635207, 0.77822334, 0.78007113, 0.78191268, 0.78373974,\n 0.78553564, 0.78731499, 0.78907371, 0.79080624, 0.79253247,\n 0.79425224, 0.79594416, 0.79762874, 0.79928778, 0.80093672,\n 0.80256446, 0.80416702, 0.80576592, 0.80735478, 0.80893549,\n 0.81050042, 0.81203815, 0.81356986, 0.81508446, 0.81658796,\n 0.81807414, 0.819548 , 0.82101567, 0.82247554, 0.82393208,\n 0.82538281, 0.8268107 , 0.82823494, 0.82965372, 0.83107178,\n 0.83248637, 0.83389408, 0.83528722, 0.83667705, 0.83806218,\n 0.83942504, 0.84078165, 0.84212383, 0.84346439, 0.84479466,\n 0.84611832, 0.84742054, 0.84871121, 0.84999906, 0.85127623,\n 0.85253753, 0.85378389, 0.85502004, 0.85624547, 0.85745736,\n 0.85866188, 0.85984637, 0.86101778, 0.86217663, 0.86332437,\n 0.86445325, 0.86558088, 0.8666952 , 0.86779646, 0.86888392,\n 0.86996579, 0.87104442, 0.87211364, 0.87317315, 0.87423006,\n 0.87527947, 0.87631514, 0.87734044, 0.87835265, 0.87936295,\n 0.88035936, 0.88134553, 0.88232488, 0.8832977 , 0.88427021,\n 0.88523831, 0.88619619, 0.88714161, 0.88807599, 0.88898991,\n 0.88989857, 0.89080345, 0.8916966 , 0.89258607, 0.89346635,\n 0.89433434, 0.89518395, 0.89603076, 0.89686706, 0.89768939,\n 0.89850803, 0.89932265, 0.90013248, 0.90093596, 0.90173482,\n 0.90251607, 0.90329546, 0.90406669, 0.90482606, 0.90557771,\n 0.90632501, 0.90706619, 0.90780234, 0.90853143, 0.90925438,\n 0.90996846, 0.91067525, 0.91137687, 0.9120734 , 0.91276691,\n 0.9134538 , 0.91412926, 0.91480048, 0.9154622 , 0.91612113,\n 0.91677252, 0.9174119 , 0.91804297, 0.91866944, 0.91929542,\n 0.91991348, 0.92052815, 0.9211373 , 0.92173916, 0.92233446,\n 0.92292101, 0.92350484, 0.92408706, 0.92466241, 0.92523367,\n 0.92579612, 0.926357 , 0.92691164, 0.92746163, 0.92800811,\n 0.92854974, 0.92908623, 0.92962044, 0.93015238, 0.93068315,\n 0.93120494, 0.93172158, 0.93223752, 0.93274696, 0.93325128,\n 0.93375434, 0.93425382, 0.93475251, 0.93524534, 0.93572834,\n 0.93620936, 0.93668669, 0.93716108, 0.93763137, 0.93809362,\n 0.93855416, 0.93901132, 0.93946516, 0.93991563, 0.94035889,\n 0.94080031, 0.94123623, 0.94166634, 0.94209054, 0.94251334,\n 0.9429314 , 0.94334561, 0.94375684, 0.94416693, 0.94457215,\n 0.94497536, 0.94537442, 0.94577212, 0.94616716, 0.94656128,\n 0.94694734, 0.94733105, 0.94771196, 0.94809051, 0.94846724,\n 0.94883789, 0.94920803, 0.94957156, 0.94992961, 0.95028537,\n 0.9506398 , 0.95099343, 0.9513436 , 0.95168786, 0.95202923,\n 0.9523691 , 0.95270547, 0.95303995, 0.95337297, 0.95370415,\n 0.95403451, 0.95436355, 0.95468948, 0.95500992, 0.95532964,\n 0.95564747, 0.95596177, 0.9562738 , 0.9565845 , 0.95689448,\n 0.95720249, 0.95750637, 0.95780805, 0.95810729, 0.95840523,\n 0.95870234, 0.9589963 , 0.95928521, 0.9595721 , 0.95985691,\n 0.9601397 , 0.9604215 , 0.96070051, 0.96097721, 0.96125114,\n 0.9615244 , 0.96179631, 0.96206536, 0.9623333 , 0.96259692,\n 0.96285944, 0.9631192 , 0.96337626, 0.96363152, 0.9638845 ,\n 0.96413674, 0.96438723, 0.96463661, 0.96488486, 0.96513187,\n 0.96537698, 0.96562037, 0.96586205, 0.96610289, 0.96634084,\n 0.96657869, 0.96681272, 0.96704657, 0.96727896, 0.96750876,\n 0.96773538, 0.96796067, 0.96818505, 0.968409 , 0.96863013,\n 0.96885103, 0.96907065, 0.96928885, 0.96950343, 0.96971703,\n 0.96992842, 0.97013804, 0.9703469 , 0.97055541, 0.97076129,\n 0.97096617, 0.9711703 , 0.97137304, 0.97157367, 0.97177272,\n 0.97196898, 0.97216465, 0.97235955, 0.97255284, 0.97274564,\n 0.97293686, 0.97312619, 0.97331534, 0.97350238, 0.97368816,\n 0.97387195, 0.9740554 , 0.9742372 , 0.97441869, 0.9745998 ,\n 0.97477959, 0.97495709, 0.97513385, 0.9753098 , 0.97548507,\n 0.97565906, 0.97583276, 0.97600475, 0.97617632, 0.97634726,\n 0.97651789, 0.97668656, 0.97685386, 0.9770202 , 0.97718552,\n 0.97735024, 0.97751419, 0.97767708, 0.97783857, 0.97799968,\n 0.97816011, 0.97831997, 0.97847803, 0.97863471, 0.97879125,\n 0.97894717, 0.97910129, 0.97925534, 0.9794075 , 0.97955873,\n 0.97970896, 0.97985833, 0.98000708, 0.9801544 , 0.98030149,\n 0.98044778, 0.98059235, 0.98073638, 0.98088019, 0.98102317,\n 0.98116567, 0.98130745, 0.98144769, 0.98158734, 0.98172653,\n 0.98186487, 0.9820027 , 0.98213961, 0.98227604, 0.98241149,\n 0.98254653, 0.98268118, 0.98281498, 0.98294806, 0.98307997,\n 0.98321127, 0.98334209, 0.98347147, 0.98360011, 0.98372841,\n 0.98385617, 0.983983 , 0.98410924, 0.98423434, 0.98435884,\n 0.98448278, 0.98460617, 0.98472912, 0.984852 , 0.98497324,\n 0.98509422, 0.98521456, 0.98533478, 0.98545394, 0.9855726 ,\n 0.98569101, 0.98580854, 0.98592469, 0.9860402 , 0.98615511,\n 0.98626975, 0.98638343, 0.9864965 , 0.98660857, 0.98672004,\n 0.98683101, 0.98694155, 0.98705146, 0.9871611 , 0.98727017,\n 0.98737845, 0.98748622, 0.98759382, 0.98770049, 0.98780695,\n 0.98791282, 0.98801809, 0.98812308, 0.98822752, 0.98833112,\n 0.98843461, 0.98853712, 0.98863913, 0.98874026, 0.98884103,\n 0.98894147, 0.98904132, 0.98914006, 0.98923872, 0.98933657,\n 0.98943426, 0.9895316 , 0.98962858, 0.98972495, 0.98982042,\n 0.98991553, 0.99001034, 0.99010474, 0.99019869, 0.99029232,\n 0.99038547, 0.99047802, 0.99056952, 0.99066046, 0.99075123,\n 0.9908412 , 0.99093095, 0.99102027, 0.99110878, 0.99119686,\n 0.991284 , 0.99137064, 0.99145684, 0.99154301, 0.9916287 ,\n 0.99171383, 0.99179822, 0.99188227, 0.99196602, 0.99204914,\n 0.99213215, 0.99221454, 0.99229625, 0.9923773 , 0.99245801,\n 0.99253818, 0.99261801, 0.99269711, 0.99277575, 0.99285437,\n 0.99293242, 0.99301037, 0.99308714, 0.99316362, 0.99323997,\n 0.99331588, 0.99339135, 0.99346645, 0.99354112, 0.99361543,\n 0.99368914, 0.99376232, 0.9938352 , 0.99390791, 0.99398013,\n 0.99405219, 0.99412331, 0.99419377, 0.994264 , 0.99433386,\n 0.99440353, 0.99447278, 0.99454165, 0.99461022, 0.99467846,\n 0.99474631, 0.99481384, 0.99488084, 0.99494741, 0.99501349,\n 0.99507947, 0.99514485, 0.99520937, 0.99527369, 0.99533783,\n 0.99540182, 0.99546534, 0.99552812, 0.99559085, 0.99565334,\n 0.99571532, 0.99577699, 0.99583833, 0.99589931, 0.9959597 ,\n 0.99601994, 0.99608004, 0.9961398 , 0.99619902, 0.99625806,\n 0.99631668, 0.99637498, 0.99643246, 0.99648964, 0.99654658,\n 0.99660348, 0.99666008, 0.99671624, 0.99677226, 0.99682789,\n 0.99688332, 0.99693851, 0.99699341, 0.99704791, 0.99710219,\n 0.99715597, 0.99720952, 0.99726274, 0.99731563, 0.99736803,\n 0.99742014, 0.99747165, 0.99752302, 0.99757402, 0.99762466,\n 0.99767508, 0.99772515, 0.99777484, 0.99782431, 0.99787324,\n 0.99792198, 0.99797022, 0.99801832, 0.99806623, 0.99811294,\n 0.99815934, 0.99820553, 0.9982516 , 0.99829736, 0.99834261,\n 0.99838751, 0.99843215, 0.99847669, 0.99852092, 0.99856455,\n 0.99860796, 0.9986511 , 0.99869369, 0.99873568, 0.99877733,\n 0.9988188 , 0.99886 , 0.99890061, 0.99894074, 0.99898074,\n 0.99902045, 0.99905956, 0.99909851, 0.99913737, 0.99917557,\n 0.99921352, 0.99925108, 0.99928825, 0.99932528, 0.99936201,\n 0.99939802, 0.99943366, 0.99946908, 0.99950427, 0.99953896,\n 0.99957313, 0.99960703, 0.99964055, 0.99967369, 0.99970635,\n 0.9997389 , 0.99977105, 0.99980226, 0.9998326 , 0.99986238,\n 0.99989173, 0.99992013, 0.99994621, 0.99997163, 0.99998665,\n 0.99999752, 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. , 1. ,\n 1. , 1. , 1. , 1. ])"},"metadata":{}}]},{"cell_type":"code","source":"plt.plot(np.cumsum(pca.explained_variance_ratio_))","metadata":{"execution":{"iopub.status.busy":"2024-02-25T06:09:21.36296Z","iopub.execute_input":"2024-02-25T06:09:21.363318Z","iopub.status.idle":"2024-02-25T06:09:21.550777Z","shell.execute_reply.started":"2024-02-25T06:09:21.363288Z","shell.execute_reply":"2024-02-25T06:09:21.549955Z"},"trusted":true},"execution_count":39,"outputs":[{"execution_count":39,"output_type":"execute_result","data":{"text/plain":"[]"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}