noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/AIDS/11. Linear Regression/Linear Regression LAB.ipynb

@@ -0,0 +1,113 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "69fb26c3-ddd3-4f19-af31-e71b71c6dba1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "\n",
+    "df = pd.read_csv('3_Linear.csv')\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b414018b-1bb9-49f6-86bd-3f1865ff0943",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c969f072-ab85-471f-a15c-6575b336951a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.pairplot(df, y_vars = ['PRICE'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22e5738a-f319-428a-94d5-224c8f87e493",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#df = df[df['PRICE'] <= df['PRICE'].quantile(0.9)]\n",
+    "x = df['PROPERTYSQFT'].to_list()\n",
+    "x = np.reshape(x, newshape = (-1,1))\n",
+    "y = df['PRICE'].to_list()\n",
+    "plt.scatter(x, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c0812fa-ecbf-466d-8d4b-cb3f0aeb8d69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = LinearRegression()\n",
+    "model.fit(x, y)\n",
+    "print(f\"Equation: y = {model.coef_}X + {model.intercept_}\")\n",
+    "print(\"Precision =\",model.score(x,y))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b06c5ce2-b4c5-4cb6-bd84-9d798d321ca2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_new = [[2000]]\n",
+    "y_pred = model.predict(x_new)\n",
+    "print(x_new, y_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bf92c6c-9fa5-45f4-914b-63a66fef4319",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(x,y, marker = '.')\n",
+    "plt.plot(x, model.predict(x), color = 'green')"
+   ]
+  }
+ ],
+ "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/11. Linear Regression/Linear Regression New- sklearn.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88872eef-23f7-49f7-97ba-a29c775e2174",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da5c81a7-ad6b-4c80-a584-90522fd94cb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv('house_rate.csv')\n",
+    "data = data.dropna()\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fa002c5a-6fb3-4360-8d7e-610c8c921984",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = data['House Size(sqft)'].to_list()\n",
+    "X = np.reshape(X, newshape = (-1,1))\n",
+    "Y = data['Price($)'].to_list()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d886cc55-92b9-413a-9889-61b564018c10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(X, Y, color = 'red')\n",
+    "plt.xlabel('Size (sq ft)')\n",
+    "plt.ylabel('Price ($)')\n",
+    "plt.title('Size vs Price of Houses')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4283f26b-e48f-461e-9f0d-e8cc8610172a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = LinearRegression()\n",
+    "model.fit(X, Y)\n",
+    "print(\"Slopes(m) =\",model.coef_)\n",
+    "print(\"Constant(c) =\",model.intercept_)\n",
+    "print(\"Linear Equation: y = mx + c\")\n",
+    "print(f\"y = {model.coef_}x + {model.intercept_}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b6b4208-94cb-48b3-8ce8-19971c9bb4af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_new = [[600]]\n",
+    "y_pred = model.predict(x_new)\n",
+    "print(\"Independent Variables:\",x_new)\n",
+    "print(\"Dependent Variable:\",y_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "728c8310-f244-421a-a453-60142b83307f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(X, Y, color = 'red', label = 'Actual')\n",
+    "plt.plot(X, model.predict(X), color = 'green', label = 'Predicted')\n",
+    "plt.legend()\n",
+    "plt.title(\"Linear Regression\")\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/AIDS CN NLP/AIDS/11. Linear Regression/Linear Regression.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "318b8eae-4e2f-48a6-aa70-270176eee584",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b93ed99b-696f-452b-9eda-123eedbc57d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = [1, 2, 3, 4, 5]\n",
+    "y = [2, 4, 5, 4, 5]\n",
+    "mean_x = np.mean(x)\n",
+    "mean_y = np.mean(y)\n",
+    "print(x)\n",
+    "print(y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4b85b82-9962-4204-a134-1293c8b8ce64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "SS_x = [(x1 - mean_x)**2 for x1 in x]\n",
+    "SS_y = [(y1 - mean_y)**2 for y1 in y]\n",
+    "SS_x, SS_y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "381241c0-715d-4197-b449-5ed3598cbe8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "product = [(x1 - mean_x)*(y1 - mean_y) for x1, y1 in zip(x, y)]\n",
+    "print(product)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "68cdd29b-8e27-49db-8096-1296e3662efd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "b1 = sum(product)/sum(SS_x)\n",
+    "b0 = mean_y - (b1*mean_x)\n",
+    "def lnr_reg(x):\n",
+    "    return b1*x + b0 #y = mx + c\n",
+    "print(f\"B0: {b0} and B1: {b1}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4cf0b80c-94c3-492d-b1bc-80ac6cb8d728",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_cap = [(b0 + b1*x1) for x1 in x]#y = mx + c (m->b1, c->b0)\n",
+    "print(y_cap)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbbeca29-6041-43b5-933c-8c921149eca4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num = sum([(y1 - y2)**2 for y1, y2 in zip(y_cap, y)])\n",
+    "num"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5206d776-9c8b-4b81-aa67-734e760a4ded",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "SE = (num/(len(x) - 2))**0.5\n",
+    "SE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db1fd839-e12a-407a-9cd3-5deb707e7f1e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if SE < 1:\n",
+    "    print(\"Standard Error =\", SE, \"So Accept The Model\")\n",
+    "else:\n",
+    "    print(\"Standard Error =\", SE, \"So Reject The Model\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d0d21e07-e52f-4144-b3f9-4dfec2978caf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Finding y value for new value of x\n",
+    "x_val = 6\n",
+    "print(\"For x =\",x_val)\n",
+    "print(f\"Linear Regression Equation: y = {b1:.2f}x + {b0:.2f}\")\n",
+    "y_val = lnr_reg(x_val)\n",
+    "print(\"y =\",y_val)"
+   ]
+  }
+ ],
+ "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/11. Linear Regression/house_rate.csv

@@ -0,0 +1,22 @@
+House Size(sqft),Price($)
+1200,500000
+1500,600000
+1700,700000
+1600,550000
+1300,580000
+1400,600000
+1000,550000
+900,480000
+800,450000
+1100,510000
+1200,550000
+1300,600000
+1600,650000
+1900,710000
+1800,690000
+2000,750000
+2100,800000
+2200,850000
+2300,900000
+2400,950000
+2500,1000000

noshot/data/AIDS CN NLP/AIDS/12. Logistic Regression/Logistic Regression New- sklearn.ipynb

@@ -0,0 +1,128 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "202c2b89-4640-4c92-9b71-468bb5344c52",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn import preprocessing\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "89500d07-8550-44f8-b65f-250d75f4484a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "data = pd.read_csv('default.csv')\n",
+    "data = data.dropna()\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b686cff0-e3bc-4de3-9ea5-1ca38aef2568",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = data['balance']\n",
+    "Y = data['student']\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0432a397-bda3-4d60-98ae-8d727d3e0c4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "catColumns = data.select_dtypes(['object']).columns\n",
+    "le = preprocessing.LabelEncoder()\n",
+    "\n",
+    "for col in catColumns:\n",
+    "    n = len(data[col].unique())\n",
+    "    if (n > 2):\n",
+    "       X = pd.get_dummies(data[col])\n",
+    "       X = X.drop(X.columns[0], axis=1)\n",
+    "       data[X.columns] = X\n",
+    "       data.drop(col, axis=1, inplace=True)  # drop the original categorical variable (optional)\n",
+    "    else:\n",
+    "       le.fit(data[col])\n",
+    "       data[col] = le.transform(data[col])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f17750f-229a-4d20-857b-2350a2937d94",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "model = LogisticRegression()\n",
+    "model.fit(np.reshape(X, newshape = (-1,1)), Y)\n",
+    "print(\"Coefficent =\",model.coef_)\n",
+    "print(\"Constant(c) =\",model.intercept_)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5e46fa9a-bed2-480f-b5b0-9ecfedcb6f0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_new = [[10000]]\n",
+    "y_pred = model.predict(x_new)\n",
+    "print(\"Balance:\",x_new[0])\n",
+    "Class = {1:'Yes', 0 : 'No'}\n",
+    "print(\"Is He Student?:\", Class[y_pred[0]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d155d2d7-a269-4766-ade2-e3fa74c33c95",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.regplot(x = X, y = Y, data = data, logistic = True, ci = None,\n",
+    "            marker = 'x', scatter_kws = {'color': 'orange'})\n",
+    "plt.title(\"Logisitc Regression\")\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/AIDS CN NLP/AIDS/12. Logistic Regression/Logistic Regression.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "48961c1d-3e9b-430d-b529-956467a3194c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "data = pd.read_csv(\"hours_scores_records.csv\")\n",
+    "print(data.shape)\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f3117a88-f1f0-45b6-8890-0893d84264a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mean_hours = data['Hours'].mean()\n",
+    "print(\"Hours Mean:\", mean_hours)\n",
+    "mean_scores = data['Scores'].mean()\n",
+    "print(\"Scores Mean:\", mean_scores)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3e023a56-1fbc-4a7d-9565-49efb6a66074",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data['Hours - Mean_Hours'] = round(data['Hours'] - mean_hours, 3)\n",
+    "mean1 = data['Hours - Mean_Hours'].mean()\n",
+    "mean1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4574bdb-b5e4-4541-978c-ceea8d30f453",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data['Scores - Mean_Scores'] = round(data['Scores'] - mean_scores, 3)\n",
+    "mean2 = data['Scores - Mean_Scores'].mean()\n",
+    "mean2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da2a298f-e92b-4161-8c5d-c38accb83eda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data['product'] = data['Hours - Mean_Hours']*data['Scores - Mean_Scores']\n",
+    "mean3 = data['product'].mean()\n",
+    "mean3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e322b3a6-89ea-4cce-bce4-45f53fefa439",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data['mean_x_squared'] = data['Scores - Mean_Scores']**2\n",
+    "data['mean_x2_squared'] = data['Hours - Mean_Hours']**2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86d7a11a-7c35-4c8e-881d-37861322cafe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mean_x2 = data['mean_x2_squared'].mean()\n",
+    "mean_x2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "107dba29-8e26-4b9d-8ec7-179999a025a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "slope = mean3/mean_x2\n",
+    "slope"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "77514aa2-58be-4c7d-aebc-2cfd1f9e2474",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c = mean2 - (slope*mean1)\n",
+    "c"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f991039c-5805-430d-952e-9012b8f4c783",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "z = (slope*(data['Hours'].astype(float))) + c\n",
+    "data[\"y\"] = 1/(1+np.exp(-z))\n",
+    "data.to_csv('score_updated.csv', index = False)\n",
+    "data.head()"
+   ]
+  }
+ ],
+ "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
+}