Upload 2 files

app.py

@@ -0,0 +1,172 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import streamlit as st
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from mlxtend.evaluate import bias_variance_decomp
+import numpy as np
+
+# Use a dark background style for plots
+plt.style.use('dark_background')
+
+# Function to generate custom data
+def generate_data(n_classes, n_samples, pattern='Linear'):
+    X = np.zeros((n_classes*n_samples, 2))
+    y = np.zeros(n_classes*n_samples, dtype='uint8')
+    for j in range(n_classes):
+        ix = range(n_samples*j, n_samples*(j+1))
+        if pattern == 'Spiral':
+            r = np.linspace(0.0, 1, n_samples) # radius
+            t = np.linspace(j*4, (j+1)*4, n_samples) + np.random.randn(n_samples)*0.2 # theta
+            X[ix] = np.c_[r*np.sin(t), r*np.cos(t)]
+        elif pattern == 'Linear':
+            X[ix] = np.random.rand(n_samples, 2) * [j * 2, 1] + np.random.randn(n_samples, 2) * 0.2
+        elif pattern == 'Concentric Circle':
+            t = np.linspace(0, 2*np.pi, n_samples)
+            r = j/float(n_classes) + np.random.randn(n_samples)*0.1
+            X[ix] = np.c_[r*np.cos(t), r*np.sin(t)]
+        elif pattern == 'Blob':
+            t = np.linspace(0, 2*np.pi, n_samples)
+            r = 0.8 + np.random.randn(n_samples)*0.1
+            X[ix] = np.c_[r*np.cos(t), r*np.sin(t)] + np.random.randn(n_samples, 2)*0.2
+        elif pattern == 'Crescent':
+            half_samples = int(n_samples / 2)
+            theta = np.linspace(j * np.pi, (j + 2) * np.pi, n_samples)
+            r = np.linspace(1.0, 2.5, half_samples)
+            r = np.concatenate((r, np.linspace(2.5, 1.0, half_samples)))
+            X[ix] = np.c_[r*np.sin(theta), r*np.cos(theta)]
+        elif pattern == 'Normal':
+            for j in range(n_classes):
+                ix = range(n_samples*j, n_samples*(j+1))
+                X[ix] = np.random.randn(n_samples, 2) * 0.5 + np.random.randn(2) * j * 2
+                y[ix] = j
+            return X, y
+        elif pattern == 'Random':
+            X[ix] = np.random.randn(n_samples, 2)*0.5 + np.random.randn(2)*j*2
+        else:
+            raise ValueError('Invalid pattern: {}'.format(pattern))
+        y[ix] = j
+    return X, y
+
+# Function to plot decision boundary and calculate model evaluation metrics
+def keffect(k):
+    X, y = generate_data(num_classes, num_data_points, pattern=pattern)
+    
+    knn = KNeighborsClassifier(n_neighbors=k)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y, random_state=42)
+    knn.fit(X_train,y_train)
+    y_pred = knn.predict(X_test)
+    
+    accuracy = accuracy_score(y_test, y_pred)
+    mse, bias, var = bias_variance_decomp(knn, X_train, y_train, X_test, y_test, loss='mse', num_rounds=200, random_seed=1)
+    
+    # Create a meshgrid for decision boundary plotting
+    a = np.arange(start=X_train[:,0].min()-1, stop=X_train[:,0].max()+1, step=0.01)
+    b = np.arange(start=X_train[:,1].min()-1, stop=X_train[:,1].max()+1, step=0.01)
+    XX, YY = np.meshgrid(a, b)
+    input_array = np.array([XX.ravel(), YY.ravel()]).T
+    labels = knn.predict(input_array)
+    
+    # Plot decision boundary
+    fig, ax = plt.subplots(figsize=(fig_width, fig_height))
+    ax.set_facecolor('#FFF')
+    ax.contourf(XX, YY, labels.reshape(XX.shape), alpha=selected_alpha, cmap='Set1', edgecolors='black')
+    scatter = ax.scatter(X[:,0], X[:,1], c=y, cmap='Set1', edgecolors='black')
+    ax.set_title('K-Nearest Neighbors (K = {})'.format(k), color='white')
+    ax.set_xlabel('Feature 1', color='white')
+    ax.set_ylabel('Feature 2', color='white')
+    ax.tick_params(axis='x', colors='white')
+    ax.tick_params(axis='y', colors='white')
+
+    # Remove top and right spines
+    ax.spines['right'].set_visible(False)
+    ax.spines['left'].set_visible(False)
+    ax.spines['top'].set_visible(False)
+    ax.spines['bottom'].set_visible(False)
+
+    result = [accuracy, mse, bias, var]
+    return fig, result
+
+# Function to plot bias-variance tradeoff
+def plot_bias_variance_tradeoff(start_value, end_value):
+    X, y = generate_data(num_classes, num_data_points, pattern=pattern)
+
+    ks = range(start_value, end_value)
+    mse, bias, var = [], [], []
+    for k in ks:
+        knn = KNeighborsClassifier(n_neighbors=k)
+        mse_k, bias_k, var_k = bias_variance_decomp(knn, X, y, X, y, loss='mse', num_rounds=200, random_seed=1)
+        mse.append(mse_k)
+        bias.append(bias_k)
+        var.append(var_k)
+
+    fig, ax = plt.subplots(figsize=(fig_width, fig_height))
+    ax.plot(ks, mse, label='MSE', color='crimson')
+    ax.plot(ks, bias, label='Bias', color='magenta')
+    ax.plot(ks, var, label='Variance', color='cyan')
+    ax.legend()
+    ax.set_title('Bias-Variance Tradeoff', color='white')
+    ax.set_xlabel('Number of Neighbors (K)', color='white')
+    ax.set_ylabel('Error', color='white')
+    ax.tick_params(axis='x', colors='white')
+    ax.tick_params(axis='y', colors='white')
+    ax.set_xticks(list(range(start_value, end_value, 5)) + [end_value])
+    ax.set_facecolor('#000')
+
+    return fig
+
+# Create a streamlit app to interact with the functions
+st.set_page_config(page_title='K-Nearest Neighbors', layout='wide')
+st.title('K-Nearest Neighbors')
+
+with st.sidebar:
+    # Set up Streamlit sidebar
+    st.sidebar.header("Plot Settings")
+    [fig_width, fig_height] = [st.sidebar.slider(label, 1, 20, default) for label, default in [("Figure Width", 10), ("Figure Height", 6)]]
+    selected_alpha = st.sidebar.slider('Select the transparency of the decision boundary', min_value=0.0, max_value=1.0, value=0.5, step=0.1)
+
+    st.write("---")
+    st.sidebar.header("Data Settings")
+    pattern = st.selectbox('Select a pattern', ['Linear', 'Concentric Circle', 'Spiral', 'Blob', 'Crescent', 'Normal', 'Random'])
+    num_classes = st.slider('Select the number of classes', min_value=2, max_value=10, value=2, step=1)
+    num_data_points = st.slider('Select the number of data points', min_value=20, max_value=200, value=40, step=20)
+
+    st.write("---")
+    st.sidebar.header("Select the number of neighbors (K)")
+    selected_k = st.slider(label="", min_value=1, max_value=50, value=3, step=1)
+    
+    st.write("---")
+    st.sidebar.header("Select a range for bias-variance tradeoff")
+    range_slider = st.slider(
+        label="",
+        min_value=1,
+        max_value=50,
+        value=(1, 20),
+        step=1
+    )
+    start_value, end_value = range_slider
+
+    st.write("---")
+
+if st.button('Get Decision Boundary'):
+    # st.write('Decision Boundary')
+    fig, result = keffect(min(selected_k, num_data_points))
+    st.write(fig)
+
+    st.write('Model evaluation metrics')
+    st.write('Accuracy:', round(result[0], 3))
+    st.write('MSE:', round(result[1], 3))
+    st.write('Bias:', round(result[2], 3))
+    st.write('Variance:', round(result[3], 3))
+
+if st.button('Get Bias-Variance Tradeoff'):
+    # st.write('Bias-Variance Tradeoff')
+    fig2 = plot_bias_variance_tradeoff(min(start_value, num_data_points), min(end_value, num_data_points))
+    st.write(fig2)
+
+
+
+    

requirement.txt

@@ -0,0 +1,312 @@
+absl-py==1.4.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+alabaster==0.7.12
+altair==4.2.2
+anaconda-client==1.7.2
+anaconda-navigator==1.9.12
+anaconda-project==0.8.3
+appdirs==1.4.4
+apyori==1.1.2
+argh==0.26.2
+asn1crypto==1.3.0
+astroid @ file:///C:/ci/astroid_1592487315634/work
+astropy==4.0.1.post1
+astunparse==1.6.3
+async-timeout==4.0.2
+atomicwrites==1.4.0
+attrs==19.3.0
+autopep8 @ file:///tmp/build/80754af9/autopep8_1592412889138/work
+Babel==2.8.0
+backcall==0.2.0
+backports.functools-lru-cache==1.6.1
+backports.shutil-get-terminal-size==1.0.0
+backports.tempfile==1.0
+backports.weakref==1.0.post1
+backports.zoneinfo==0.2.1
+bcrypt==3.1.7
+beautifulsoup4==4.9.1
+bitarray @ file:///C:/ci/bitarray_1594751093906/work
+bkcharts==0.2
+bleach==3.1.5
+blinker==1.6.2
+bokeh @ file:///C:/ci/bokeh_1593178781838/work
+boto==2.49.0
+Bottleneck==1.3.2
+brotlipy==0.7.0
+cachetools==5.3.0
+certifi==2020.6.20
+cffi==1.14.0
+chardet==3.0.4
+charset-normalizer==2.0.12
+click==7.1.2
+cloudpickle @ file:///tmp/build/80754af9/cloudpickle_1594141588948/work
+clyent==1.2.2
+colorama==0.4.3
+comtypes==1.1.7
+conda==4.10.1
+conda-build==3.18.11
+conda-package-handling==1.7.0
+conda-verify==3.4.2
+contextlib2==0.6.0.post1
+cryptography==2.9.2
+cycler==0.10.0
+Cython==0.29.23
+cytoolz==0.10.1
+dask @ file:///tmp/build/80754af9/dask-core_1594156306305/work
+dateparser==1.1.1
+decorator==4.4.2
+defusedxml==0.6.0
+diff-match-patch @ file:///tmp/build/80754af9/diff-match-patch_1594828741838/work
+distlib==0.3.2
+distributed @ file:///C:/ci/distributed_1594742844291/work
+docopt==0.6.2
+docutils==0.16
+entrypoints==0.3
+et-xmlfile==1.0.1
+etils==1.0.0
+fastcache==1.1.0
+filelock==3.0.12
+flake8==3.8.3
+Flask==1.1.2
+flatbuffers==2.0.7
+frozenlist==1.3.0
+fsspec==0.7.4
+future==0.18.2
+gast==0.4.0
+gensim==4.1.2
+gevent @ file:///C:/ci/gevent_1593005471151/work
+gitdb==4.0.10
+GitPython==3.1.31
+glob2==0.7
+gmpy2==2.0.8
+google-auth==2.16.1
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+greenlet==0.4.16
+grpcio==1.51.3
+h5py==2.10.0
+HeapDict==1.0.1
+html5lib @ file:///tmp/build/80754af9/html5lib_1593446221756/work
+idna @ file:///tmp/build/80754af9/idna_1593446292537/work
+imageio @ file:///tmp/build/80754af9/imageio_1594161405741/work
+imagesize==1.2.0
+importlib-metadata==6.0.0
+importlib-resources==5.12.0
+intervaltree @ file:///tmp/build/80754af9/intervaltree_1594361675072/work
+ipykernel @ file:///C:/ci/ipykernel_1594745408489/work/dist/ipykernel-5.3.2-py3-none-any.whl
+ipython @ file:///C:/ci/ipython_1593447482397/work
+ipython_genutils==0.2.0
+ipywidgets==7.5.1
+isort==4.3.21
+itsdangerous==1.1.0
+jax==0.3.14
+jaxlib==0.3.14
+jdcal==1.4.1
+jedi @ file:///C:/ci/jedi_1592833825077/work
+Jinja2==2.11.2
+joblib @ file:///tmp/build/80754af9/joblib_1594236160679/work
+json5==0.9.5
+jsonschema==3.2.0
+jupyter==1.0.0
+jupyter-client @ file:///tmp/build/80754af9/jupyter_client_1594826976318/work
+jupyter-console==6.1.0
+jupyter-core==4.6.3
+jupyterlab==2.1.5
+jupyterlab-server @ file:///tmp/build/80754af9/jupyterlab_server_1594164409481/work
+keras==2.11.0
+keyring @ file:///C:/ci/keyring_1593109799227/work
+kiwisolver==1.2.0
+lazy-object-proxy==1.4.3
+libarchive-c==2.9
+libclang==15.0.6.1
+llvmlite==0.33.0
+locket==0.2.0
+lxml @ file:///C:/ci/lxml_1594822774489/work
+Markdown==3.4.1
+markdown-it-py==2.2.0
+MarkupSafe==1.1.1
+matplotlib @ file:///C:/ci/matplotlib-base_1592837548929/work
+mccabe==0.6.1
+mdurl==0.1.2
+menuinst==1.4.16
+mistune==0.8.4
+mkl-fft==1.1.0
+mkl-random==1.1.1
+mkl-service==2.3.0
+mlxtend @ file:///home/conda/feedstock_root/build_artifacts/mlxtend_1606368531479/work
+mne==1.3.1
+mock==4.0.2
+more-itertools==8.4.0
+mpmath==1.1.0
+msgpack==1.0.0
+multidict==6.0.2
+multipledispatch==0.6.0
+navigator-updater==0.2.1
+nbconvert==5.6.1
+nbformat==5.0.7
+networkx @ file:///tmp/build/80754af9/networkx_1594377231366/work
+nltk @ file:///tmp/build/80754af9/nltk_1592496090529/work
+nose==1.3.7
+notebook==6.0.3
+numba==0.50.1
+numexpr==2.7.1
+numpy==1.23.1
+numpydoc @ file:///tmp/build/80754af9/numpydoc_1594166760263/work
+oauthlib==3.2.2
+olefile==0.46
+openpyxl @ file:///tmp/build/80754af9/openpyxl_1594167385094/work
+opt-einsum==3.3.0
+packaging==20.4
+pandas @ file:///C:/ci/pandas_1592833613419/work
+pandocfilters==1.4.2
+paramiko==2.7.1
+parso==0.7.0
+partd==1.1.0
+path==13.1.0
+pathlib2==2.3.5
+pathtools==0.1.2
+patsy==0.5.1
+pep8==1.7.1
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow @ file:///C:/ci/pillow_1594298230227/work
+pipreqs==0.4.13
+pkginfo==1.5.0.1
+platformdirs==3.2.0
+pluggy==0.13.1
+ply==3.11
+pooch==1.7.0
+praw==7.5.0
+prawcore==2.3.0
+prometheus-client==0.8.0
+prompt-toolkit==3.0.5
+protobuf==3.19.6
+psutil==5.7.0
+py @ file:///tmp/build/80754af9/py_1593446248552/work
+pyarrow==11.0.0
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycodestyle==2.6.0
+pycosat==0.6.3
+pycparser @ file:///tmp/build/80754af9/pycparser_1594388511720/work
+pycurl==7.43.0.5
+pydeck==0.8.1b0
+pydocstyle @ file:///tmp/build/80754af9/pydocstyle_1592848020240/work
+pyflakes==2.2.0
+Pygments==2.15.1
+pylint @ file:///C:/ci/pylint_1592482039483/work
+Pympler==1.0.1
+PyNaCl @ file:///C:/ci/pynacl_1595000047588/work
+pyodbc===4.0.0-unsupported
+pyOpenSSL @ file:///tmp/build/80754af9/pyopenssl_1594392929924/work
+pyparsing==2.4.7
+pyreadline==2.1
+pyrsistent==0.16.0
+PySocks==1.7.1
+pytest==5.4.3
+python-binance==1.0.15
+python-dateutil==2.8.1
+python-jsonrpc-server @ file:///tmp/build/80754af9/python-jsonrpc-server_1594397536060/work
+python-language-server @ file:///C:/ci/python-language-server_1594162130238/work
+pytz==2020.1
+pytz-deprecation-shim==0.1.0.post0
+PyWavelets==1.1.1
+pywin32==227
+pywin32-ctypes==0.2.0
+pywinpty==0.5.7
+PyYAML==5.3.1
+pyzmq==19.0.1
+QDarkStyle==2.8.1
+QtAwesome==0.7.2
+qtconsole @ file:///tmp/build/80754af9/qtconsole_1592848611704/work
+QtPy==1.9.0
+regex @ file:///C:/ci/regex_1593419644658/work
+requests @ file:///tmp/build/80754af9/requests_1592841827918/work
+requests-oauthlib==1.3.1
+rich==13.3.4
+rope==0.17.0
+rsa==4.9
+Rtree==0.9.4
+ruamel_yaml==0.15.87
+scikit-image==0.16.2
+scikit-learn @ file:///C:/ci/scikit-learn_1592853510272/work
+scipy @ file:///C:/ci/scipy_1592916963468/work
+seaborn==0.10.1
+Send2Trash==1.5.0
+simplegeneric==0.8.1
+singledispatch==3.4.0.3
+sip==4.19.13
+six==1.15.0
+smart-open==5.2.1
+smmap==5.0.0
+snowballstemmer==2.0.0
+sortedcollections==1.2.1
+sortedcontainers==2.2.2
+soupsieve==2.0.1
+Sphinx @ file:///tmp/build/80754af9/sphinx_1594223420021/work
+sphinxcontrib-applehelp==1.0.2
+sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-htmlhelp==1.0.3
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-serializinghtml==1.1.4
+sphinxcontrib-websupport @ file:///tmp/build/80754af9/sphinxcontrib-websupport_1593446360927/work
+spyder @ file:///C:/ci/spyder_1594830825244/work
+spyder-kernels @ file:///C:/ci/spyder-kernels_1594751670175/work
+SQLAlchemy @ file:///C:/ci/sqlalchemy_1593445271541/work
+statsmodels==0.11.1
+streamlit==1.21.0
+sympy @ file:///C:/ci/sympy_1594234545115/work
+tables==3.6.1
+tblib==1.6.0
+tensorboard==2.11.2
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.11.0
+tensorflow-estimator==2.11.0
+tensorflow-intel==2.11.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==2.2.0
+terminado==0.8.3
+testpath==0.4.4
+textblob==0.17.1
+threadpoolctl @ file:///tmp/tmp9twdgx9k/threadpoolctl-2.1.0-py3-none-any.whl
+toml @ file:///tmp/build/80754af9/toml_1592853716807/work
+toolz==0.10.0
+tornado==6.0.4
+tqdm @ file:///tmp/build/80754af9/tqdm_1593446365756/work
+traitlets==4.3.3
+typing_extensions==4.5.0
+tzdata==2022.1
+tzlocal==4.1
+ujson==1.35
+unicodecsv==0.14.1
+update-checker==0.18.0
+urllib3==1.25.9
+validators==0.20.0
+virtualenv==20.4.7
+virtualenvwrapper-win==1.2.6
+watchdog @ file:///C:/ci/watchdog_1593447437088/work
+wcwidth @ file:///tmp/build/80754af9/wcwidth_1593447189090/work
+webencodings==0.5.1
+websocket-client==1.3.1
+websockets==9.1
+Werkzeug==1.0.1
+widgetsnbextension==3.5.1
+win-inet-pton==1.1.0
+win-unicode-console==0.5
+wincertstore==0.2
+wrapt==1.11.2
+xlrd==1.2.0
+XlsxWriter==1.2.9
+xlwings==0.19.5
+xlwt==1.3.0
+xmltodict==0.12.0
+yapf @ file:///tmp/build/80754af9/yapf_1593528177422/work
+yarg==0.1.9
+yarl==1.7.2
+zict==2.0.0
+zipp==3.1.0
+zope.event==4.4
+zope.interface==4.7.1