noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/AIDS/10. ANOVA/One Way ANOVA (Repeated Measure).ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0c5491e5-16d7-48af-9c5c-4656cc870c22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from scipy import stats"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "240a2de4-c0b4-4edc-a26c-c1eb5b688af3",
+   "metadata": {},
+   "source": [
+    "<b>Does sleep deprivation cause us to be either more or less aggressie? To test\n",
+    "    this assumption, a psychologist randomly assigns volunteer subjects to sleep-deprivation\n",
+    "    periods of either 0, 24, or 48 hours (independent variable). Subsequently, subjects are tested\n",
+    "    for agressive behaviour. Aggressioin scores (dependent variable) indicate the total number of \n",
+    "    different agressive behaviour.\n",
+    "</b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "68731695-7b9e-4b8a-a7f1-5ccee8454842",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def ANOVA_REP(groups, alpha):\n",
+    "    group_mean = [np.mean(group) for group in groups]\n",
+    "    subject_mean = [np.mean(subject) for subject in zip(*groups)]\n",
+    "    grand_mean = np.mean(group_mean)\n",
+    "    k = len(groups)\n",
+    "    N = sum([len(group) for group in groups])\n",
+    "    SSB = sum( len(group) * (group_mean[i] - grand_mean)**2 \\\n",
+    "                for i, group in enumerate(groups) )\n",
+    "    SSW = sum( (x - group_mean[i])**2 \\\n",
+    "                for i, group in enumerate(groups) for x in group )\n",
+    "    SSS = sum( k * (subject_mean[i] - grand_mean)**2 \\\n",
+    "                for i, group in enumerate(groups) )\n",
+    "    SSE = SSW - SSS\n",
+    "    dfb = k - 1\n",
+    "    dfw = N - k\n",
+    "    dfs = len(groups[0]) - 1\n",
+    "    dfe = dfw - dfs\n",
+    "    MSB = SSB/dfb\n",
+    "    MSE = SSE/dfe\n",
+    "    F = MSB/MSE\n",
+    "    critical = stats.f.ppf(1-alpha, dfb, dfe)\n",
+    "\n",
+    "    print(\"Critical Value =\", critical)\n",
+    "    print(\"F Statistic =\", F)\n",
+    "    if F > critical: \n",
+    "        print(\"Reject Null Hypothesis\")\n",
+    "    else:\n",
+    "        print(\"Accept Null Hypothesis\")\n",
+    "\n",
+    "    x = np.linspace(0, 50, 1000) #adjust as required\n",
+    "    y = stats.f.pdf(x, dfb, dfe)\n",
+    "    plt.figure(figsize = (10, 8)) #adjust if you need to\n",
+    "    plt.plot(x, y, color = 'blue', label = 'F Distribution')\n",
+    "    plt.axvline(x = F, color = 'green', linestyle = '--', label = 'F Statistic')\n",
+    "    plt.fill_between(x, y, color = 'red', where = (x > critical), alpha = 0.5, label = 'Critical Region')\n",
+    "\n",
+    "    plt.xlabel('F Score')\n",
+    "    plt.ylabel('Probability Density')\n",
+    "    plt.title('One Way ANOVA (Repeated Measure) Test')\n",
+    "    plt.legend()\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "57dcb781-e81a-4f37-a900-6a8389480ddd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('sleep_deprivation.csv')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "874682bf-61dc-460a-92e1-ef075a410398",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groups = [df['Zero'], df['Twenty_Four'], df['Forty_Eight']]\n",
+    "groups = [list(x) for x in groups]\n",
+    "alpha = 0.05\n",
+    "ANOVA_REP(groups, alpha)"
+   ]
+  }
+ ],
+ "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/AIDS CN NLP/AIDS/10. ANOVA/One Way ANOVA.ipynb

@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0fcaaf6e-3185-4a2f-b4e9-f2f295b1c88d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import random\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba7494c2-fc54-4fb1-b5de-28bc61904c23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def ANOVA(groups, alpha):\n",
+    "    group_mean = [np.mean(group) for group in groups]\n",
+    "    grand_mean = np.mean(group_mean)\n",
+    "    k = len(groups)\n",
+    "    N = sum([len(group) for group in groups])\n",
+    "    SSB = sum( len(group) * (group_mean[i] - grand_mean)**2 \\\n",
+    "                for i, group in enumerate(groups) )\n",
+    "    SSW = sum( (x - group_mean[i])**2 \\\n",
+    "                for i, group in enumerate(groups) for x in group )\n",
+    "    dfb = k - 1\n",
+    "    dfw = N - k\n",
+    "    MSB = SSB/dfb\n",
+    "    MSW = SSW/dfw\n",
+    "    F = MSB/MSW\n",
+    "    critical = stats.f.ppf(1-alpha, dfb, dfw)\n",
+    "\n",
+    "    print(\"Critical Value =\", critical)\n",
+    "    print(\"F Statistic =\", F)\n",
+    "    if F > critical: \n",
+    "        print(\"Reject Null Hypothesis\")\n",
+    "    else:\n",
+    "        print(\"Accept Null Hypothesis\")\n",
+    "\n",
+    "    x = np.linspace(0, 6, 1000)\n",
+    "    y = stats.f.pdf(x, dfb, dfw)\n",
+    "    plt.figure(figsize = (10, 6))\n",
+    "    plt.plot(x, y, color = 'blue', label = 'F Distribution')\n",
+    "    plt.axvline(x = F, color = 'green', linestyle = '--', label = 'F Statistic')\n",
+    "    plt.fill_between(x, y, color = 'red', where = (x > critical), alpha = 0.5, label = 'Critical Region')\n",
+    "\n",
+    "    plt.xlabel('F Score')\n",
+    "    plt.ylabel('Probability Density')\n",
+    "    plt.title('One Way ANOVA Test')\n",
+    "    plt.legend()\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b9460934-9472-4cea-b804-258f6cd5fa33",
+   "metadata": {},
+   "source": [
+    "<b>Implement Random Sampling, Demonstrate ANOVA. \n",
+    "Is there a significant difference in the DiabetesPedigreeFunction levels between young adults (20-30), middle-aged adults (31-50), and older adults (50+) diagnosed with diabetes?\n",
+    "</b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0bd5d561-99d0-4e2a-8146-a86140809a07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('2_ANOVA.csv')\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7dfab0a1-f7eb-4b98-80a7-8c916634006f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def categorize(age):\n",
+    "    if 20 <= age <= 30: return \"young\"\n",
+    "    elif 30 < age <= 50: return \"middle-aged\"\n",
+    "    elif 50 < age: return \"old\"\n",
+    "\n",
+    "df['Age_Category'] = df['Age'].apply(categorize)\n",
+    "df[['DiabetesPedigreeFunction', 'Age', 'Age_Category']].head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ac1d0667-cde4-4d91-af95-8e50e1b155c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groups = df.groupby('Age_Category')['DiabetesPedigreeFunction'].apply(list)\n",
+    "groups = [random.choices(group, k = 50) for group in groups]\n",
+    "alpha = 0.05\n",
+    "ANOVA(groups, alpha)"
+   ]
+  }
+ ],
+ "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/AIDS CN NLP/AIDS/10. ANOVA/Sample 1 Way ANOVA Test.ipynb

@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c96adcb7-b9d3-444a-ab9e-b8a191af58a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "960be4dd-22a3-45e7-8f75-680209a6513d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_curve(F_statistic, critical_value, df_between, df_within):\n",
+    "    x = np.linspace(0, 12, 1000)  # Range for F-distribution\n",
+    "    y = stats.f.pdf(x, df_between, df_within)  # PDF of F-distribution\n",
+    "    plt.figure(figsize=(10, 6))\n",
+    "    plt.plot(x, y, label='F-distribution', color='blue')\n",
+    "\n",
+    "    # Shade the critical region\n",
+    "    plt.fill_between(x, y, where=(x > critical_value), color='red', alpha=0.5, label='Critical Region')\n",
+    "    \n",
+    "    # Draw the F-statistic line\n",
+    "    plt.axvline(F_statistic, color='orange', linestyle='--', label='F-statistic')\n",
+    "    \n",
+    "    plt.title('ANOVA: F-Distribution and Critical Region')\n",
+    "    plt.xlabel('F Value')\n",
+    "    plt.ylabel('Probability Density')\n",
+    "    plt.legend()\n",
+    "    plt.grid()\n",
+    "    plt.xlim(0, 12)  # Adjust x-axis limits\n",
+    "    plt.ylim(0, max(y) * 1.1)  # Adjust y-axis limits for better visibility\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "409dfa77-3937-4b66-a8be-5dcb1960e6a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 1: Load the dataset\n",
+    "file_path = 'sample_data.csv'  # Replace with the path to your CSV file\n",
+    "df = pd.read_csv(file_path)\n",
+    "df = df.dropna()\n",
+    "# Assume 'School' is the categorical column and 'Values' is the numerical column.\n",
+    "# Step 2: Group the data by 'School' and calculate means\n",
+    "groups = df.groupby('School')['Values']\n",
+    "group_means = groups.mean()\n",
+    "overall_mean = df['Values'].mean()\n",
+    "\n",
+    "# Step 3: Calculate SSB (Sum of Squares Between)\n",
+    "SSB = sum(groups.size()[group] * (group_mean - overall_mean) ** 2 \n",
+    "           for group, group_mean in group_means.items())\n",
+    "\n",
+    "# Step 4: Calculate SSW (Sum of Squares Within)\n",
+    "SSW = sum(((group_data - group_means[group_name]) ** 2).sum() \n",
+    "           for group_name, group_data in groups)\n",
+    "\n",
+    "# Step 5: Degrees of freedom\n",
+    "df_between = len(group_means) - 1  # k - 1\n",
+    "df_within = len(df) - len(group_means)  # N - k\n",
+    "\n",
+    "# Step 6: Calculate MSB and MSW\n",
+    "MSB = SSB / df_between\n",
+    "MSW = SSW / df_within\n",
+    "\n",
+    "# Step 7: Calculate the F-statistic\n",
+    "F_statistic = MSB / MSW\n",
+    "\n",
+    "# Step 8: Determine the critical F-value from the F-distribution table\n",
+    "alpha = 0.05  # Significance level\n",
+    "critical_value = stats.f.ppf(1 - alpha, df_between, df_within)\n",
+    "\n",
+    "# Step 9: Print results\n",
+    "print(f\"F-statistic: {F_statistic:.2f}\")\n",
+    "print(f\"Critical F-value: {critical_value:.2f}\")\n",
+    "\n",
+    "show_curve(F_statistic, critical_value, df_between, df_within)\n",
+    "# Step 10: Decision - Reject or Fail to Reject Null Hypothesis\n",
+    "if F_statistic > critical_value:\n",
+    "    print(\"Reject the null hypothesis (There is a significant difference between group means).\")\n",
+    "else:\n",
+    "    print(\"Fail to reject the null hypothesis (No significant difference between group means).\")"
+   ]
+  }
+ ],
+ "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/AIDS CN NLP/AIDS/10. ANOVA/Two Way ANOVA.ipynb

@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e356560-a7fa-44fd-bc9f-08becb1209c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a6db50e0-3436-418d-99eb-e0e1ee7b6485",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_curve(x, y, F, critical, title):\n",
+    "        plt.figure(figsize = (10, 8)) #adjust if you need to\n",
+    "        plt.plot(x, y, color = 'blue', label = 'F Distribution')\n",
+    "        plt.axvline(x = F, color = 'green', linestyle = '--', label = 'F Statistic')\n",
+    "        plt.fill_between(x, y, color = 'red', where = (x > critical), alpha = 0.5, label = 'Critical Region')\n",
+    "        plt.xlabel('F Score')\n",
+    "        plt.ylabel('Probability Density')\n",
+    "        plt.title(title)\n",
+    "        plt.legend()\n",
+    "        plt.show()\n",
+    "def Two_Way_ANOVA(groups, row_groups, col_groups, alpha):\n",
+    "    cell_mean = [np.mean(group) for group in groups]\n",
+    "    col_mean = [np.mean(col) for col in col_groups]\n",
+    "    row_mean = [np.mean(row) for row in row_groups]\n",
+    "    grand_mean = np.mean(cell_mean)\n",
+    "    \n",
+    "    k = len(groups)\n",
+    "    N = sum([len(group) for group in groups])\n",
+    "    c = len(col_groups)\n",
+    "    r = len(row_groups)\n",
+    "    SSB = sum( len(group) * (cell_mean[i] - grand_mean)**2 \\\n",
+    "                for i, group in enumerate(groups) )\n",
+    "    SSW = sum( (x - cell_mean[i])**2 \\\n",
+    "                for i, group in enumerate(groups) for x in group )\n",
+    "    SSC = sum( len(col) * (col_mean[i] - grand_mean)**2 \\\n",
+    "                for i, col in enumerate(col_groups) )\n",
+    "    SSR = sum( len(row) * (row_mean[i] - grand_mean)**2 \\\n",
+    "                for i, row in enumerate(row_groups) )\n",
+    "    SSI = SSB - (SSC + SSR)\n",
+    "    dfb = k - 1\n",
+    "    dfc = c - 1\n",
+    "    dfr = r - 1\n",
+    "    dfi = dfc*dfr\n",
+    "    dfw = N - c*r\n",
+    "    MSC = SSC/dfc\n",
+    "    MSR = SSR/dfr\n",
+    "    MSI = SSI/dfi\n",
+    "    MSW = SSW/dfw\n",
+    "\n",
+    "    F_col = MSC/MSW\n",
+    "    F_row = MSR/MSW\n",
+    "    F_intr = MSI/MSW \n",
+    "    critical_col = stats.f.ppf(1-alpha, dfc, dfw)\n",
+    "    critical_row = stats.f.ppf(1-alpha, dfr, dfw)\n",
+    "    critical_intr = stats.f.ppf(1-alpha, dfi, dfw)\n",
+    "\n",
+    "    print(\"Critical Vaue =\", critical_col, \"\\tF Column =\", F_col)\n",
+    "    print(\"Critical Vaue =\", critical_row, \"\\tF Row =\", F_row)\n",
+    "    print(\"Critical Vaue =\", critical_intr, \"\\tF Interaction =\", F_intr)\n",
+    "    if F_col > critical_col or F_row > critical_row | F_intr > critical_intr: \n",
+    "        print(\"Reject Null Hypothesis\")\n",
+    "    else:\n",
+    "        print(\"Accept Null Hypothesis\")\n",
+    "\n",
+    "    x = np.linspace(0, 6, 1000)\n",
+    "    y_col = stats.f.pdf(x, dfc, dfw)\n",
+    "    y_row = stats.f.pdf(x, dfr, dfw)\n",
+    "    y_intr = stats.f.pdf(x, dfi, dfw)\n",
+    "    show_curve(x, y_col, F_col, critical_col, \"F Column\")\n",
+    "    show_curve(x, y_row, F_row, critical_row, \"F Row\")\n",
+    "    show_curve(x, y_intr, F_intr, critical_intr, \"F Interaction\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8d52120-5d61-4f59-9781-f368ee14f6b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('reaction_time.csv')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3b28a0b-45eb-4178-9201-358c6897fc04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1 = df[df['Degree of Danger'] == 'Dangerous']\n",
+    "df2 = df[df['Degree of Danger'] == 'Nondangerous']\n",
+    "\n",
+    "groups = [df1['Zero'], df1['Two'], df1['Four'], df2['Zero'], df2['Two'], df2['Four']]\n",
+    "row_groups = []\n",
+    "for _, cell in df.groupby(['Degree of Danger']):\n",
+    "    row_groups.append([*cell['Zero'].values , *cell['Two'].values, *cell['Four'].values])\n",
+    "col_groups = [df['Zero'], df['Two'], df['Four']]\n",
+    "alpha = 0.05\n",
+    "Two_Way_ANOVA(groups,row_groups, col_groups, alpha)"
+   ]
+  }
+ ],
+ "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/AIDS CN NLP/AIDS/10. ANOVA/reaction_time.csv

@@ -0,0 +1,5 @@
+Degree of Danger,Zero,Two,Four
+Dangerous,8,8,10
+Dangerous,8,6,8
+Nondangerous,9,15,24
+Nondangerous,11,19,18

noshot/data/AIDS CN NLP/AIDS/10. ANOVA/sample_data.csv

@@ -0,0 +1,16 @@
+School,Values
+A,85
+A,90
+A,88
+A,82
+A,87
+B,78
+B,80
+B,82
+B,79
+B,85
+C,92
+C,88
+C,85
+C,90
+C,89

noshot/data/AIDS CN NLP/AIDS/10. ANOVA/sleep_deprivation.csv

@@ -0,0 +1,4 @@
+Subject,Zero,Twenty_Four,Forty_Eight
+A,0,3,6
+B,4,6,8
+C,2,6,10