Taariq Mowzer and Justine Verwey

EDA.ipynb

@@ -0,0 +1,373 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8c27d092",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "594e37d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_train = pd.read_csv('data/returns_train.csv', index_col='month_end')\n",
+    "df_train.sort_index()\n",
+    "df_test = pd.read_csv('data/returns_test.csv', index_col='month_end')\n",
+    "df_test.sort_index();"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab9a7f05",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all = pd.concat([df_train, df_test])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23429d59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f59d07e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f45c8e11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stocks = df_train.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0c19773d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1 + df_train.Stock1).cumprod().plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e173c714",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(df_all.columns)\n",
+    "1/54"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "adeead11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for stock in stocks:\n",
+    "    ax = (1 + df_all[stock]).cumprod().plot()\n",
+    "ax.axvline(len(df_train), c='r')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "876417ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1 + df_all.Stock66).cumprod().plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2604ffcd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1 + df_all.Stock54).cumprod().plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a5291f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d1e14611",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1 + df_all).cumprod().loc[['2017-09-30']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a079265d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all.Stock54.iloc[-13:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "602b26ea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pypfopt.expected_returns import mean_historical_return\n",
+    "from pypfopt.risk_models import CovarianceShrinkage\n",
+    "df_train_cum = (df_train + 1).cumprod()\n",
+    "mu = mean_historical_return(df_train_cum)\n",
+    "S = CovarianceShrinkage(df_train_cum).ledoit_wolf()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "893784c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22396233",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pypfopt.efficient_frontier import EfficientFrontier\n",
+    "ef = EfficientFrontier(mu, S, weight_bounds=(0,0.1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2ba7e90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "weights = ef.max_sharpe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9524682f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list(weights.keys)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc685705",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def dict_to_df(dic):\n",
+    "    new_dic = {}\n",
+    "    for key in dic:\n",
+    "        new_dic[key] = [dic[key]]\n",
+    "\n",
+    "    return pd.DataFrame(new_dic)\n",
+    "dict_to_df(weights)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4a2cf47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1.5)**(1/(4*12))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d147a818",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(1.07)**(1/12) - 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2e99242",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.stats import normaltest\n",
+    "\n",
+    "for i in range(len(df_all)):\n",
+    "    print(normaltest(df_all[stocks[i]])[1])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f64a8ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_all[stocks[7]].hist(bins=30)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc03e60d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(df_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e13378b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "scatter_data = []\n",
+    "for stock in stocks:\n",
+    "    series = df_all[stock]\n",
+    "    for i in range(len(series) - 1):\n",
+    "        scatter_data.append([series[i], series[i + 1]])\n",
+    "x = [i[0] for i in scatter_data]\n",
+    "y = [i[1] for i in scatter_data]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "636e23ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.stats import linregress\n",
+    "linregress(x, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fe3791a9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.stats import pearsonr\n",
+    "pearsonr(x, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "874962a9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len({'a': 1, 'b': 5})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4fd8af38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter([i[0] for i in scatter_data], [i[1] for i in scatter_data])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "78714014",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pypfopt.risk_models import CovarianceShrinkage, semicovariance, risk_matrix\n",
+    "risk_df = risk_matrix((1 + df_train).cumprod(), method='sample_cov')\n",
+    "\n",
+    "for i in range(len(risk_df)):\n",
+    "    for j in range(len(risk_df)):\n",
+    "        risk_df.iloc[i, j] /= (risk_df.iloc[i, i]*risk_df.iloc[j, j])**0.5\n",
+    "        \n",
+    "risk_df"
+   ]
+  }
+ ],
+ "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}