noshot 0.4.1__tar.gz → 1.0.0__tar.gz

{noshot-0.4.1 → noshot-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: noshot
-Version: 0.4.1
+Version: 1.0.0
 Summary: Support library for Artificial Intelligence, Machine Learning and Data Science tools
 Author: Tim Stan S
 License: MIT

{noshot-0.4.1 → noshot-1.0.0}/noshot.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: noshot
-Version: 0.4.1
+Version: 1.0.0
 Summary: Support library for Artificial Intelligence, Machine Learning and Data Science tools
 Author: Tim Stan S
 License: MIT

noshot-1.0.0/noshot.egg-info/SOURCES.txt

@@ -0,0 +1,35 @@
+LICENSE.txt
+README.md
+setup.py
+noshot.egg-info/PKG-INFO
+noshot.egg-info/SOURCES.txt
+noshot.egg-info/dependency_links.txt
+noshot.egg-info/not-zip-safe
+noshot.egg-info/top_level.txt
+src/noshot/__init__.py
+src/noshot/main.py
+src/noshot/data/ML TS XAI/TS/10. Seasonal ARIMA Forecasting.ipynb
+src/noshot/data/ML TS XAI/TS/11. Multivariate ARIMA Forecasting.ipynb
+src/noshot/data/ML TS XAI/TS/6. ACF PACF.ipynb
+src/noshot/data/ML TS XAI/TS/7. Differencing.ipynb
+src/noshot/data/ML TS XAI/TS/8. ARMA Forecasting.ipynb
+src/noshot/data/ML TS XAI/TS/9. ARIMA Forecasting.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/EDA2_chipsdatset.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/EDA_IRISH_8thjan.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/XAI_EX1 MODEL BIAS (FINAL).ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/complete_guide_to_eda_on_text_data.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/deepchecksframeworks.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/deepexplainers (mnist).ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/guidedbackpropagation.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/updated_image_EDA1_with_LRP.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 1/zebrastripes.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/EXP_5.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp-3 (EDA-loan).ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp-3 (EDA-movie).ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp-4(Flower dataset).ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp-4.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp_2.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/Exp_7.ipynb
+src/noshot/data/ML TS XAI/XAI/XAI 2/FeatureImportance_SensitivityAnalysis.ipynb
+src/noshot/utils/__init__.py
+src/noshot/utils/shell_utils.py

{noshot-0.4.1 → noshot-1.0.0}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as f:
 
 setup(
     name="noshot",
-    version="0.4.1",
+    version="1.0.0",
     author="Tim Stan S",
     description="Support library for Artificial Intelligence, Machine Learning and Data Science tools",
     long_description=long_description,

noshot-1.0.0/src/noshot/data/ML TS XAI/TS/10. Seasonal ARIMA Forecasting.ipynb

@@ -0,0 +1,246 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "142adfce-1c93-475a-a465-0f344cbc6b93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "from pandas.plotting import autocorrelation_plot\n",
+    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+    "import statsmodels.api as sm\n",
+    "from statsmodels.tsa.arima_model import ARIMA\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b10b8b58-6c78-442e-b712-67b16f228f15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('monthly-sunspots.csv', parse_dates=[0])\n",
+    "df.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3b123997-e868-4998-bbb6-9031ea8ab39f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(10,8))\n",
+    "plt.plot(df['Month'], df['Sunspots'], color = 'green', label = 'Sunspot Numbers')\n",
+    "plt.xlabel('Date')\n",
+    "plt.ylabel('Sunspot Numbers')\n",
+    "plt.grid()\n",
+    "plt.title('Monthly Mean Sunspot Numbers')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c56e5d1-a019-457b-8313-c5f71b378a5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.describe().T"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "94752ac3-fb85-41c1-94dc-f1a05b0baf75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Month'] = pd.to_datetime(df['Month'])\n",
+    "data_new = df.set_index(df['Month'])\n",
+    "data_new = data_new.drop(labels = ['Month'], axis = 1)\n",
+    "data_new.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b02c91b4-f7ee-4ce5-b707-6bf2604bed55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(10,8))\n",
+    "data_new['Sunspots'].plot(style = 'k.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dca190cd-41b8-44d5-8ed2-190c87b04fb9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_q = data_new.resample('q').mean()\n",
+    "data_q.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f944805-6b99-4854-a7c2-53bf2a6de1c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def adfuller_test(data):\n",
+    "    result = adfuller(data)\n",
+    "    labels = ['ADF Test Statistic' 'P-value', 'Lags Used', 'Number of Observation Used']\n",
+    "    for value, label in zip(result, labels):\n",
+    "        print(label+\": \"+str(value))\n",
+    "    if result[1] <= 0.05:\n",
+    "        print(\"Strong evidencew against the null hypothesis(h0), reject the null hypothesis. Data has no unit root and is stationary\")\n",
+    "    else:\n",
+    "        print(\"Weak evidence against null hypothesis, time series has a unit root, indicating it is non-stationary\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e2740f4-ba2b-4fc4-a310-131b15ae20cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_q.plot(figsize=(10,8))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8062e59f-4149-45fc-b2ca-3f586c6ed078",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_data = data_q.copy()\n",
+    "base_data['Monthly Mean Total Sunspot Number'] = base_data['Sunspots']\n",
+    "base_data['Shifter Monthly Mean Total Sunspot Number'] = base_data['Monthly Mean Total Sunspot Number'].shift(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8232f405-2560-4b9a-870e-8af209ef0f87",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9cb81777-9f8d-4c64-ad4f-7c245454085e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_data[['Monthly Mean Total Sunspot Number', 'Shifter Monthly Mean Total Sunspot Number']].plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e27fde3-cef9-4366-a972-52a974226d91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_data = base_data.dropna()\n",
+    "print(\"Mean Squared Error:\", mean_squared_error(base_data['Monthly Mean Total Sunspot Number'], \n",
+    "                                                base_data['Shifter Monthly Mean Total Sunspot Number']))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd01e7eb-5e88-41e8-9ddd-1ea35f054b4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(10,8))\n",
+    "autocorrelation_plot(data_q)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d127256-a9cc-431d-95ae-6f8323aa21b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize=(10,8))\n",
+    "ax1 = fig.add_subplot(211)\n",
+    "fig = sm.graphics.tsa.plot_acf(data_q, lags = 40, ax = ax1)\n",
+    "ax2 = fig.add_subplot(212)\n",
+    "fig = sm.graphics.tsa.plot_pacf(data_q, lags = 40, ax = ax2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03258c9e-a3b6-465b-98ca-d5cc6a481626",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = sm.tsa.statespace.SARIMAX(data_q['Sunspots'], order=(2,0,2), seasonal_order=(2,0,2,6))\n",
+    "results = model.fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4eb643eb-59ae-475c-9096-87e536da8e62",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c2350c09-4c80-4c24-88d8-3b645981ce21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_q['forecast'] = results.predict(start = 1000, end = 1084, dynamic = True)\n",
+    "data_q[['Sunspots', 'forecast']].plot(figsize = (10,8))"
+   ]
+  }
+ ],
+ "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-1.0.0/src/noshot/data/ML TS XAI/TS/11. Multivariate ARIMA Forecasting.ipynb

@@ -0,0 +1,228 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8f9faf6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from statsmodels.tsa.stattools import adfuller\n",
+    "from statsmodels.tsa.stattools import grangercausalitytests\n",
+    "from statsmodels.tsa.statespace.varmax import VARMAX\n",
+    "from statsmodels.tsa.api import VAR\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da824655",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "custom_column_names = ['WSR0','WSR1']\n",
+    "df = pd.read_csv('eighthr.csv', parse_dates=[0], na_values=['?'],\n",
+    "                 index_col=0, names = (['WSR0', 'WSR1']+list(range(3, 74))))\n",
+    "df = df.dropna()\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92bf562d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['WSR0'] = df['WSR0'].astype(float)\n",
+    "df['WSR1'] = df['WSR1'].astype(float)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f578482e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig,axes = plt.subplots(2,1,figsize=(14,8))\n",
+    "df['WSR1'].plot(ax=axes[0],title='WSR0')\n",
+    "df['WSR0'].plot(ax=axes[1],title='WSR1')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "daac380f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = adfuller(df['WSR0'])\n",
+    "print(result)\n",
+    "if result[1]<0.05:\n",
+    "    print(\"It is Stationary\")\n",
+    "else:\n",
+    "    print(\"It is not stationary\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e18f51f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = adfuller(df['WSR1'])\n",
+    "print(result)\n",
+    "if result[1]<0.05:\n",
+    "    print(\"It is Stationary\")\n",
+    "else:\n",
+    "    print(\"It is not stationary\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b6419c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print('WSR0 causes WSR1')\n",
+    "print('---------------------')\n",
+    "granger1=grangercausalitytests(df[['WSR0','WSR1']],2)\n",
+    "print('WSR1 causes WSR0')\n",
+    "print('---------------------')\n",
+    "granger1=grangercausalitytests(df[['WSR1','WSR0']],2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37f4f93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train = df[['WSR0','WSR1']]\n",
+    "model = VAR(train)\n",
+    "sortedmodel = model.select_order(maxlags=20)\n",
+    "sortedmodel.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3da00920",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = VARMAX(df[['WSR0', 'WSR1']], order=(10,0),enforce_stationarity=True)\n",
+    "model_fit = model.fit()\n",
+    "model_fit.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b0cf16d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "n_forecast = 12\n",
+    "pred = model_fit.get_prediction()\n",
+    "preds = pred.predicted_mean"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "56954749",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "preds.columns = ['WSR0 Predictions','WSR1 Predictions']\n",
+    "preds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "704c6372",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train = df[['WSR0','WSR1']]\n",
+    "testvspread = pd.concat([train,preds],axis=1)\n",
+    "testvspread"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d60e3508",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testvspread[['WSR0','WSR0 Predictions']].plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "28fb2660",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testvspread[['WSR1','WSR1 Predictions']].plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35888acd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import mean_squared_error\n",
+    "mean_squared_error(testvspread['WSR1'],testvspread['WSR1 Predictions'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41748e7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import mean_squared_error\n",
+    "mean_squared_error(testvspread['WSR0'],testvspread['WSR0 Predictions'])"
+   ]
+  }
+ ],
+ "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-1.0.0/src/noshot/data/ML TS XAI/TS/6. ACF PACF.ipynb

@@ -0,0 +1,77 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "97b25ae4-1eb7-4599-bad4-e959bbb9a275",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f70584ab-aa4d-4957-9315-3e884f66c559",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('daily-min-temperatures.csv')\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b6574dd0-e010-423b-bb26-ba2ca142e848",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(title = \"daily Minimum Temperature\" ,figsize = (14, 8), legend = None, color = 'green')\n",
+    "plt.xlabel('Date')\n",
+    "plt.ylabel('Temperature (°C)')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3ba0f2ea-069c-4aa2-aa4b-0d90a54ee21f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, axs = plt.subplots(2, 1, figsize = (10,8))\n",
+    "plot_acf(df['Temp'], lags = 30, ax = axs[0], title = 'Autocorrelation (ACF)', color = 'green')\n",
+    "plot_pacf(df['Temp'], lags = 30, ax = axs[1], title = 'Partial Autocorrelation (PACF)', color = 'red')\n",
+    "plt.tight_layout()\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
+}