noshot 0.4.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

noshot/data/ML TS XAI/TS/7. Differencing.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ac778c2-495b-4613-80ca-d6be2b71e598",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a843538d-035e-4a90-b67b-1fa647c22f70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('daily-min-temperatures.csv', parse_dates = ['Date'], index_col = 'Date')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3aff0e1-9c54-474f-83ea-2b6bb632bd3f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(title = 'Daily Minimum Temperatures', figsize = (14, 8), legend = None)\n",
+    "plt.xlabel('Date')\n",
+    "plt.ylabel('Temperature (°C)')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d08b196-75c8-473d-b77e-85008048d590",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "differenced_series = df.diff(periods=1) #lag-1 difference\n",
+    "plt.subplot(2, 1, 1)\n",
+    "plt.plot(df, label = \"Original Series\")\n",
+    "plt.title(\"Original Daily Minimum Temperatures\")\n",
+    "plt.grid()\n",
+    "\n",
+    "plt.subplot(2, 1, 2)\n",
+    "plt.plot(differenced_series, label = \"Differneced Series\", color=\"green\")\n",
+    "plt.title(\"Differneced Daily Minimum Temperatures\")\n",
+    "plt.grid()\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "800dd56a-1b3f-4cdd-8fac-802048d1160b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df.values\n",
+    "diff = []\n",
+    "days_in_year =  365\n",
+    "for i in range(days_in_year, len(X)):\n",
+    "    value = X[i] - X[i - days_in_year]\n",
+    "    diff.append(value)\n",
+    "plt.plot(diff)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1dc499f8-4c1d-4d65-9e16-3439fe22ef13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['diff'] = df['Temp'].diff(periods=1)\n",
+    "\n",
+    "plt.plot(df.index, df['Temp'], label = 'Original')\n",
+    "plt.plot(df.index, df['diff'], label = 'Differenced (lag-1)')\n",
+    "plt.xlabel('Date')\n",
+    "plt.ylabel('Temperature (°C)')\n",
+    "plt.title(\"Temperature Time Series with Differencing\")\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7f720228-762a-48e3-aa61-733846cca105",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('daily-min-temperatures.csv', header=0, index_col = 0)\n",
+    "X = [i%365 for i in range(0, len(df))]\n",
+    "y = df.values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "87262e57-a216-422d-a768-2d2459df23ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "degree = 4\n",
+    "coef = np.polyfit(X, y, degree)\n",
+    "print(\"Coefficients:\\n\", coef)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "daec417d-061a-4953-9d2b-206dbc0ba8e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "curve = []\n",
+    "for i in range(len(X)):\n",
+    "    value = coef[-1]\n",
+    "    for d in range(degree):\n",
+    "        value += (X[i]**(degree - d)) * coef[d]\n",
+    "        curve.append(value)\n",
+    "\n",
+    "values = df.values\n",
+    "\n",
+    "diff = []\n",
+    "for i in range(len(values)):\n",
+    "    value = values[i] - curve[i]\n",
+    "    diff.append(value)\n",
+    "\n",
+    "plt.plot(diff)\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/ML TS XAI/TS/8. ARMA Forecasting.ipynb

@@ -0,0 +1,197 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb446765-5f1b-4827-8eb8-465f275c1821",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats\n",
+    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+    "from statsmodels.graphics.api import qqplot\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "from statsmodels.api import tsa\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8166c848-99fb-4883-9534-372e66da163f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('monthly-sunspots.csv', index_col = 'YEAR')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5db24ed8-03ae-4136-9d39-b7315daa85a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(figsize=(15,8), color = 'purple')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9288a36-b6b8-4492-9dc7-276d9a185f63",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(15,8))\n",
+    "ax1 = fig.add_subplot(211)\n",
+    "fig = plot_acf(df.values.squeeze(), lags=40, ax=ax1, color = 'r', title='Original Autocorrelation')\n",
+    "ax2 = fig.add_subplot(212)\n",
+    "fig = plot_pacf(df, lags=40, ax=ax2, color = 'g', title='Original Partial Autocorrelation')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4044bdd-d852-49af-882a-7cf238abd1b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "arma20 = ARIMA(df, order=(2,0,0)).fit()\n",
+    "display(arma20.params)\n",
+    "display(arma20.aic, arma20.bic, arma20.hqic)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "653f3938-1703-4cac-969a-1d991aed2081",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "arma30 = ARIMA(df, order=(3,0,0)).fit()\n",
+    "display(arma30.params)\n",
+    "display(arma30.aic, arma30.bic, arma30.hqic)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d5f9d78e-9638-4c1f-bded-1d9a9a377543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(15,8))\n",
+    "ax = fig.add_subplot(111)\n",
+    "ax = arma30.resid.plot(ax=ax)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "790a3e2d-486d-4406-aa1b-58c1c50d904f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "resid = arma30.resid\n",
+    "stats.normaltest(resid)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20212ba9-efa8-4bb9-88b8-5bd8c1a99a3d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(15,8))\n",
+    "ax = fig.add_subplot(111)\n",
+    "fig = qqplot(resid, line='q', ax=ax, fit=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e50e8ade-7027-4ed9-91f4-c4bd9119ad4a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(15,8))\n",
+    "ax1 = fig.add_subplot(211)\n",
+    "fig = plot_acf(resid.values.squeeze(), lags=40, ax=ax1, color='g', title='Residual Autocorrelation')\n",
+    "ax2 = fig.add_subplot(212)\n",
+    "fig = plot_pacf(resid, lags=40, ax=ax2, color='r', title='Residual Partial Autocorrelation')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6b5a13b-3ce6-4be3-9e6b-436435d79141",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "r, q, p = tsa.acf(resid.values.squeeze(), fft=True, qstat=True)\n",
+    "data = np.c_[np.arange(1, 25), r[1:], q, p]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "87267a9d-ebfa-4324-b5ae-45c5680af95a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.DataFrame(data, columns = ['Lag', 'AC', 'Q', 'Prob(>Q)'])\n",
+    "df2.set_index('Lag')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cccb84e-4a8e-4278-b8a5-ed592936d84b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predict_sunspots = arma30.predict('1990', '2012', dynamic=True)\n",
+    "predict_sunspots = predict_sunspots['1990-12-31':'2008-12-31']\n",
+    "predict_sunspots = pd.DataFrame(predict_sunspots)\n",
+    "predict_sunspots.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74f236dc-3062-4395-a444-bbeb411e8460",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.mean((df['1990-12-31':'2008-12-31':1]['SUNACTIVITY'].values  - predict_sunspots['predicted_mean'].values))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/ML TS XAI/TS/9. ARIMA Forecasting.ipynb

@@ -0,0 +1,220 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6e3f5839-6844-42c3-a57c-5e6324c7ee43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats\n",
+    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+    "from statsmodels.graphics.api import qqplot\n",
+    "from statsmodels.tsa.arima.model import ARIMA\n",
+    "from statsmodels.tsa.stattools import adfuller\n",
+    "from statsmodels.api import tsa\n",
+    "from sklearn.metrics import r2_score\n",
+    "from sklearn.model_selection import TimeSeriesSplit\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f32d68f1-db8f-4b74-b23e-2f3ad3b56eed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('monthly-sunspots.csv', index_col = 'YEAR')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "500a40bd-7d8f-4d52-923a-ad76d590216f",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "df.plot(figsize=(15,8), color = 'purple')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6dc6f56f-93bd-4506-b32a-e0f7361829b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = adfuller(df['SUNACTIVITY'])\n",
+    "display(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13ece976-8c18-4a2e-b44a-49fa6bc6ff85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pvalue =  result[1]\n",
+    "if pvalue < 0.05:\n",
+    "    print(\"Stationary\")\n",
+    "else:\n",
+    "    print(\"Non Stationary\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d83cf3f0-244b-4961-8ff4-dedf97e5a766",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plot_acf(df['SUNACTIVITY'], lags = 40)\n",
+    "plot_pacf(df['SUNACTIVITY'], lags = 40)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5dacfe47-b35b-46e4-a06f-6001040a6405",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = ARIMA(list(df['SUNACTIVITY']), order = (1,0,1))\n",
+    "result = model.fit()\n",
+    "pred = result.predict()\n",
+    "print(r2_score(df, pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "171168aa-f0a2-43f1-a195-72b9f3791a53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.plot(list(df['SUNACTIVITY']))\n",
+    "plt.plot(pred, linestyle = '--')\n",
+    "plt.legend(['Actual Sunspots'], ['Predicted SUnspots'])\n",
+    "plt.xlabel('Timesteps')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62e74f51-e0b4-4b22-856b-5a28838375b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ax = pd.Series(result.resid).hist()\n",
+    "ax.set_xlabel('Residual')\n",
+    "ax.set_ylabel('Number of Occurences')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1cac3ae4-d8f2-49c4-a04d-fabf5290977a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3ae6db1-4b9c-4a9b-8286-b6484fabb348",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_array = df.values\n",
+    "avg_errors = []\n",
+    "for p in range(1):\n",
+    "    for q in range(13):\n",
+    "        errors = []\n",
+    "        tscv = TimeSeriesSplit(test_size = 10)\n",
+    "        for train_index, test_index in tscv.split(data_array):\n",
+    "            x_train, x_test = data_array[train_index], data_array[test_index]\n",
+    "            x_test_orig = x_test\n",
+    "\n",
+    "            fcst = []\n",
+    "            for stop in range(10):\n",
+    "                try:\n",
+    "                    mod = ARIMA(x_train, order = (p,0,q))\n",
+    "                    res = mod.fit()\n",
+    "                    fcst.append(res.forecast(steps = 1))\n",
+    "                except:\n",
+    "                    print(\"Error\")\n",
+    "                    fcst.append(-9999999.)\n",
+    "                x_train = np.concatenate((x_train, x_test[0:1,]))\n",
+    "                x_test = x_test[1:]\n",
+    "            errors.append(r2_score(x_test_orig, fcst))\n",
+    "        pq_result = [p, q, np.mean(errors)]\n",
+    "        print(pq_result)\n",
+    "        avg_errors.append(pq_result)\n",
+    "avg_errors = pd.DataFrame(avg_errors)\n",
+    "avg_errors.columns = ['p', 'q', 'error']\n",
+    "result = avg_errors.pivot(index = 'p', columns = 'q')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0882bbd-e5de-4249-b74c-9f96c6777205",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dta_array = df.values\n",
+    "X_train, X_test = dta_array[:10], dta_array[-10:]\n",
+    "X_test_orig = X_test\n",
+    "\n",
+    "fcst = []\n",
+    "for step in range(10):\n",
+    "    mod = ARIMA(X_train, order = (10,0,9))\n",
+    "    res = mod.fit()\n",
+    "    fcst.append(res.forecast(steps = 1))\n",
+    "    X_train = np.concatenate((X_train, X_test[0:1,:]))\n",
+    "    X_test = X_test[1:]\n",
+    "\n",
+    "plt.plot(X_test_orig)\n",
+    "plt.plot(fcst)\n",
+    "plt.legend(['Actual Sunspots', 'Predicted Sunspots'])\n",
+    "plt.xlabel('Time Steps of Test Data')\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/main.py

@@ -1,19 +1,19 @@
-from noshot.utils.shell_utils import get_folder
-from noshot.utils.shell_utils import get_file
-from noshot.utils.shell_utils import remove_folder
-
-available = {'-1  ' : "ML TS XAI(Folder)",
-             '0   ' : "Remove Folder"}
-
-def get(name = None, open = False):
-    try:
-        if name is not None:
-            name = str(name)
-        if name in ['-1']   :   get_folder("ML TS XAI", loc = True)
-        elif name in ['0']  :   remove_folder("ML TS XAI")
-        else:
-            for k, v in available.items():
-                sep = " : " if v else ""
-                print(k,v,sep = sep)
-    except Exception as error:
+from noshot.utils.shell_utils import get_folder
+from noshot.utils.shell_utils import get_file
+from noshot.utils.shell_utils import remove_folder
+
+available = {'-1  ' : "ML TS XAI(Folder)",
+             '0   ' : "Remove Folder"}
+
+def get(name = None, open = False):
+    try:
+        if name is not None:
+            name = str(name)
+        if name in ['-1']   :   get_folder("ML TS XAI", loc = True)
+        elif name in ['0']  :   remove_folder("ML TS XAI")
+        else:
+            for k, v in available.items():
+                sep = " : " if v else ""
+                print(k,v,sep = sep)
+    except Exception as error:
         print(error)

noshot/utils/__init__.py

@@ -1,3 +1,3 @@
-from .shell_utils import get_file
-from .shell_utils import get_folder
+from .shell_utils import get_file
+from .shell_utils import get_folder
 from .shell_utils import remove_folder