diff --git a/01/01.ipynb b/01/01.ipynb
new file mode 100644
index 0000000..a214535
--- /dev/null
+++ b/01/01.ipynb
@@ -0,0 +1,3225 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "d8b075bb",
+ "metadata": {},
+ "source": [
+ "1. 导入第三方库\n",
+ "\n",
+ "导入 `pandas` 库(简写为 `pd`)和 `numpy` 库(简写为 `np`),并查看当前 pandas 的版本号。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "f169edcf",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:01.500043Z",
+ "iopub.status.busy": "2026-10-09T06:33:01.499261Z",
+ "iopub.status.idle": "2026-10-09T06:33:02.597959Z",
+ "shell.execute_reply": "2026-10-09T06:33:02.594498Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'3.0.5'"
+ ]
+ },
+ "execution_count": 1,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "pd.__version__"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "fc7ecd30",
+ "metadata": {},
+ "source": [
+ "2. 检测文件编码\n",
+ "\n",
+ "用 `chardet` 检测 `datasets/CRSP_Daily_Market_1926_2025.csv` 的编码,并打印检测到的编码名称和置信度。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "dfa09aff",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:02.606664Z",
+ "iopub.status.busy": "2026-10-09T06:33:02.605648Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.151917Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.148567Z"
+ }
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ascii 1.0\n"
+ ]
+ }
+ ],
+ "source": [
+ "import chardet\n",
+ "\n",
+ "\n",
+ "def check_encoding(file):\n",
+ " with open(file, 'rb') as f:\n",
+ " result = chardet.detect(f.read())\n",
+ " return result\n",
+ "\n",
+ "\n",
+ "file = 'datasets/CRSP_Daily_Market_1926_2025.csv'\n",
+ "result = check_encoding(file)\n",
+ "print(result['encoding'], result['confidence'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d90188b1",
+ "metadata": {},
+ "source": [
+ "3. 读取 CSV 数据\n",
+ "\n",
+ "先读前 5 行确认格式无误,再完整读取,结果赋值给变量 `crsp`。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "7c765c07",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.166344Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.163147Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.243394Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.240225Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 27366756.0 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 27424620.0 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 27479722.0 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 27538025.0 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 27561757.0 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 27620380.0 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 27526838.0 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 27585177.0 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt vwUsdCnt \\\n",
+ "0 1925-12-31 NaN NaN 27487487 NaN 500 NaN \n",
+ "1 1926-01-02 0.005689 0.005689 27600297 27366756.0 494 491.0 \n",
+ "2 1926-01-04 0.000706 0.000706 27577892 27479722.0 499 492.0 \n",
+ "3 1926-01-05 -0.004821 -0.004867 27530213 27561757.0 498 496.0 \n",
+ "4 1926-01-06 -0.000423 -0.000427 27618773 27526838.0 502 497.0 \n",
+ "\n",
+ " ewretd ewretx ewTotVal ewUsdVal ewTotCnt ewUsdCnt sprtrn \\\n",
+ "0 NaN NaN 27545352 NaN 503 NaN NaN \n",
+ "1 0.009516 0.009516 27658600 27424620.0 497 494.0 NaN \n",
+ "2 0.005780 0.005780 27636515 27538025.0 502 495.0 NaN \n",
+ "3 -0.001927 -0.002030 27588552 27620380.0 501 499.0 NaN \n",
+ "4 0.001182 0.001155 27676674 27585177.0 505 500.0 NaN \n",
+ "\n",
+ " spindx \n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN "
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp = pd.read_csv(file, nrows=5)\n",
+ "crsp"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a68db303",
+ "metadata": {},
+ "source": [
+ "确认格式无误后,完整读取:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "3bcce878",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.253945Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.253116Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.573377Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.569920Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 2.736676e+07 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 2.742462e+07 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 2.747972e+07 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 2.753802e+07 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 2.756176e+07 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 2.762038e+07 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 2.752684e+07 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 2.758518e+07 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 26296 | \n",
+ " 2025-12-24 | \n",
+ " 0.002914 | \n",
+ " 0.002904 | \n",
+ " 88568121481 | \n",
+ " 8.831774e+10 | \n",
+ " 9126 | \n",
+ " 9126.0 | \n",
+ " 0.003368 | \n",
+ " 0.003125 | \n",
+ " 90141105180 | \n",
+ " 8.988752e+10 | \n",
+ " 9498 | \n",
+ " 9498.0 | \n",
+ " 0.003221 | \n",
+ " 6932.05 | \n",
+ "
\n",
+ " \n",
+ " | 26297 | \n",
+ " 2025-12-26 | \n",
+ " -0.000242 | \n",
+ " -0.000325 | \n",
+ " 88542581122 | \n",
+ " 8.856811e+10 | \n",
+ " 9124 | \n",
+ " 9124.0 | \n",
+ " -0.002105 | \n",
+ " -0.002373 | \n",
+ " 90125553062 | \n",
+ " 9.014109e+10 | \n",
+ " 9496 | \n",
+ " 9496.0 | \n",
+ " -0.000304 | \n",
+ " 6929.94 | \n",
+ "
\n",
+ " \n",
+ " | 26298 | \n",
+ " 2025-12-29 | \n",
+ " -0.004191 | \n",
+ " -0.004230 | \n",
+ " 88169518843 | \n",
+ " 8.854242e+10 | \n",
+ " 9123 | \n",
+ " 9123.0 | \n",
+ " -0.008373 | \n",
+ " -0.008603 | \n",
+ " 89739994612 | \n",
+ " 9.012539e+10 | \n",
+ " 9495 | \n",
+ " 9495.0 | \n",
+ " -0.003492 | \n",
+ " 6905.74 | \n",
+ "
\n",
+ " \n",
+ " | 26299 | \n",
+ " 2025-12-30 | \n",
+ " -0.001550 | \n",
+ " -0.001576 | \n",
+ " 88028533719 | \n",
+ " 8.816264e+10 | \n",
+ " 9132 | \n",
+ " 9121.0 | \n",
+ " -0.002831 | \n",
+ " -0.003547 | \n",
+ " 89596162338 | \n",
+ " 8.973311e+10 | \n",
+ " 9504 | \n",
+ " 9493.0 | \n",
+ " -0.001376 | \n",
+ " 6896.24 | \n",
+ "
\n",
+ " \n",
+ " | 26300 | \n",
+ " 2025-12-31 | \n",
+ " -0.007319 | \n",
+ " -0.007491 | \n",
+ " 87552025121 | \n",
+ " 8.802809e+10 | \n",
+ " 9134 | \n",
+ " 9131.0 | \n",
+ " -0.005245 | \n",
+ " -0.005627 | \n",
+ " 89118194675 | \n",
+ " 8.959572e+10 | \n",
+ " 9506 | \n",
+ " 9503.0 | \n",
+ " -0.007358 | \n",
+ " 6845.50 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
26301 rows × 15 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "0 1925-12-31 NaN NaN 27487487 NaN 500 \n",
+ "1 1926-01-02 0.005689 0.005689 27600297 2.736676e+07 494 \n",
+ "2 1926-01-04 0.000706 0.000706 27577892 2.747972e+07 499 \n",
+ "3 1926-01-05 -0.004821 -0.004867 27530213 2.756176e+07 498 \n",
+ "4 1926-01-06 -0.000423 -0.000427 27618773 2.752684e+07 502 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 2025-12-24 0.002914 0.002904 88568121481 8.831774e+10 9126 \n",
+ "26297 2025-12-26 -0.000242 -0.000325 88542581122 8.856811e+10 9124 \n",
+ "26298 2025-12-29 -0.004191 -0.004230 88169518843 8.854242e+10 9123 \n",
+ "26299 2025-12-30 -0.001550 -0.001576 88028533719 8.816264e+10 9132 \n",
+ "26300 2025-12-31 -0.007319 -0.007491 87552025121 8.802809e+10 9134 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal ewTotCnt \\\n",
+ "0 NaN NaN NaN 27545352 NaN 503 \n",
+ "1 491.0 0.009516 0.009516 27658600 2.742462e+07 497 \n",
+ "2 492.0 0.005780 0.005780 27636515 2.753802e+07 502 \n",
+ "3 496.0 -0.001927 -0.002030 27588552 2.762038e+07 501 \n",
+ "4 497.0 0.001182 0.001155 27676674 2.758518e+07 505 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 9126.0 0.003368 0.003125 90141105180 8.988752e+10 9498 \n",
+ "26297 9124.0 -0.002105 -0.002373 90125553062 9.014109e+10 9496 \n",
+ "26298 9123.0 -0.008373 -0.008603 89739994612 9.012539e+10 9495 \n",
+ "26299 9121.0 -0.002831 -0.003547 89596162338 8.973311e+10 9504 \n",
+ "26300 9131.0 -0.005245 -0.005627 89118194675 8.959572e+10 9506 \n",
+ "\n",
+ " ewUsdCnt sprtrn spindx \n",
+ "0 NaN NaN NaN \n",
+ "1 494.0 NaN NaN \n",
+ "2 495.0 NaN NaN \n",
+ "3 499.0 NaN NaN \n",
+ "4 500.0 NaN NaN \n",
+ "... ... ... ... \n",
+ "26296 9498.0 0.003221 6932.05 \n",
+ "26297 9496.0 -0.000304 6929.94 \n",
+ "26298 9495.0 -0.003492 6905.74 \n",
+ "26299 9493.0 -0.001376 6896.24 \n",
+ "26300 9503.0 -0.007358 6845.50 \n",
+ "\n",
+ "[26301 rows x 15 columns]"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp = pd.read_csv(file)\n",
+ "crsp"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "87494a86",
+ "metadata": {},
+ "source": [
+ "4. 初步认识数据\n",
+ "\n",
+ "查看 `crsp` 的行数和列数(`shape`)、前 5 行(`head()`)和后 5 行(`tail()`),并打印出所有的列名。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "4325fafa",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.581013Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.580182Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.594550Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.591208Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(26301, 15)"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "144d4409",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.603520Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.601637Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.672477Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.667803Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 27366756.0 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 27424620.0 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 27479722.0 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 27538025.0 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 27561757.0 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 27620380.0 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 27526838.0 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 27585177.0 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt vwUsdCnt \\\n",
+ "0 1925-12-31 NaN NaN 27487487 NaN 500 NaN \n",
+ "1 1926-01-02 0.005689 0.005689 27600297 27366756.0 494 491.0 \n",
+ "2 1926-01-04 0.000706 0.000706 27577892 27479722.0 499 492.0 \n",
+ "3 1926-01-05 -0.004821 -0.004867 27530213 27561757.0 498 496.0 \n",
+ "4 1926-01-06 -0.000423 -0.000427 27618773 27526838.0 502 497.0 \n",
+ "\n",
+ " ewretd ewretx ewTotVal ewUsdVal ewTotCnt ewUsdCnt sprtrn \\\n",
+ "0 NaN NaN 27545352 NaN 503 NaN NaN \n",
+ "1 0.009516 0.009516 27658600 27424620.0 497 494.0 NaN \n",
+ "2 0.005780 0.005780 27636515 27538025.0 502 495.0 NaN \n",
+ "3 -0.001927 -0.002030 27588552 27620380.0 501 499.0 NaN \n",
+ "4 0.001182 0.001155 27676674 27585177.0 505 500.0 NaN \n",
+ "\n",
+ " spindx \n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN "
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "0b122155",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.680628Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.679612Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.773686Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.767599Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 26296 | \n",
+ " 2025-12-24 | \n",
+ " 0.002914 | \n",
+ " 0.002904 | \n",
+ " 88568121481 | \n",
+ " 8.831774e+10 | \n",
+ " 9126 | \n",
+ " 9126.0 | \n",
+ " 0.003368 | \n",
+ " 0.003125 | \n",
+ " 90141105180 | \n",
+ " 8.988752e+10 | \n",
+ " 9498 | \n",
+ " 9498.0 | \n",
+ " 0.003221 | \n",
+ " 6932.05 | \n",
+ "
\n",
+ " \n",
+ " | 26297 | \n",
+ " 2025-12-26 | \n",
+ " -0.000242 | \n",
+ " -0.000325 | \n",
+ " 88542581122 | \n",
+ " 8.856811e+10 | \n",
+ " 9124 | \n",
+ " 9124.0 | \n",
+ " -0.002105 | \n",
+ " -0.002373 | \n",
+ " 90125553062 | \n",
+ " 9.014109e+10 | \n",
+ " 9496 | \n",
+ " 9496.0 | \n",
+ " -0.000304 | \n",
+ " 6929.94 | \n",
+ "
\n",
+ " \n",
+ " | 26298 | \n",
+ " 2025-12-29 | \n",
+ " -0.004191 | \n",
+ " -0.004230 | \n",
+ " 88169518843 | \n",
+ " 8.854242e+10 | \n",
+ " 9123 | \n",
+ " 9123.0 | \n",
+ " -0.008373 | \n",
+ " -0.008603 | \n",
+ " 89739994612 | \n",
+ " 9.012539e+10 | \n",
+ " 9495 | \n",
+ " 9495.0 | \n",
+ " -0.003492 | \n",
+ " 6905.74 | \n",
+ "
\n",
+ " \n",
+ " | 26299 | \n",
+ " 2025-12-30 | \n",
+ " -0.001550 | \n",
+ " -0.001576 | \n",
+ " 88028533719 | \n",
+ " 8.816264e+10 | \n",
+ " 9132 | \n",
+ " 9121.0 | \n",
+ " -0.002831 | \n",
+ " -0.003547 | \n",
+ " 89596162338 | \n",
+ " 8.973311e+10 | \n",
+ " 9504 | \n",
+ " 9493.0 | \n",
+ " -0.001376 | \n",
+ " 6896.24 | \n",
+ "
\n",
+ " \n",
+ " | 26300 | \n",
+ " 2025-12-31 | \n",
+ " -0.007319 | \n",
+ " -0.007491 | \n",
+ " 87552025121 | \n",
+ " 8.802809e+10 | \n",
+ " 9134 | \n",
+ " 9131.0 | \n",
+ " -0.005245 | \n",
+ " -0.005627 | \n",
+ " 89118194675 | \n",
+ " 8.959572e+10 | \n",
+ " 9506 | \n",
+ " 9503.0 | \n",
+ " -0.007358 | \n",
+ " 6845.50 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "26296 2025-12-24 0.002914 0.002904 88568121481 8.831774e+10 9126 \n",
+ "26297 2025-12-26 -0.000242 -0.000325 88542581122 8.856811e+10 9124 \n",
+ "26298 2025-12-29 -0.004191 -0.004230 88169518843 8.854242e+10 9123 \n",
+ "26299 2025-12-30 -0.001550 -0.001576 88028533719 8.816264e+10 9132 \n",
+ "26300 2025-12-31 -0.007319 -0.007491 87552025121 8.802809e+10 9134 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal ewTotCnt \\\n",
+ "26296 9126.0 0.003368 0.003125 90141105180 8.988752e+10 9498 \n",
+ "26297 9124.0 -0.002105 -0.002373 90125553062 9.014109e+10 9496 \n",
+ "26298 9123.0 -0.008373 -0.008603 89739994612 9.012539e+10 9495 \n",
+ "26299 9121.0 -0.002831 -0.003547 89596162338 8.973311e+10 9504 \n",
+ "26300 9131.0 -0.005245 -0.005627 89118194675 8.959572e+10 9506 \n",
+ "\n",
+ " ewUsdCnt sprtrn spindx \n",
+ "26296 9498.0 0.003221 6932.05 \n",
+ "26297 9496.0 -0.000304 6929.94 \n",
+ "26298 9495.0 -0.003492 6905.74 \n",
+ "26299 9493.0 -0.001376 6896.24 \n",
+ "26300 9503.0 -0.007358 6845.50 "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.tail()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "5c970fb8",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.782768Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.782062Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.800097Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.797167Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['DlyCalDt', 'vwretd', 'vwretx', 'vwTotVal', 'vwUsdVal', 'vwTotCnt',\n",
+ " 'vwUsdCnt', 'ewretd', 'ewretx', 'ewTotVal', 'ewUsdVal', 'ewTotCnt',\n",
+ " 'ewUsdCnt', 'sprtrn', 'spindx'],\n",
+ " dtype='str')"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.columns"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5648828a",
+ "metadata": {},
+ "source": [
+ "5. 数据的基本信息与统计摘要\n",
+ "\n",
+ "用 `info()` 和 `describe()` 查看 `crsp` 的列类型和统计摘要。`vwretd` 等列名中,vw = value-weighted 市值加权,ew = equal-weighted 等权重;`sprtrn`、`spindx` 两列从 1962 年 7 月才开始有数据,所以非缺失值个数明显更少。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "0cc3d4d8",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.818847Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.817266Z",
+ "iopub.status.idle": "2026-10-09T06:33:07.874233Z",
+ "shell.execute_reply": "2026-10-09T06:33:07.868076Z"
+ }
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "RangeIndex: 26301 entries, 0 to 26300\n",
+ "Data columns (total 15 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 DlyCalDt 26301 non-null str \n",
+ " 1 vwretd 26300 non-null float64\n",
+ " 2 vwretx 26300 non-null float64\n",
+ " 3 vwTotVal 26301 non-null int64 \n",
+ " 4 vwUsdVal 26300 non-null float64\n",
+ " 5 vwTotCnt 26301 non-null int64 \n",
+ " 6 vwUsdCnt 26300 non-null float64\n",
+ " 7 ewretd 26300 non-null float64\n",
+ " 8 ewretx 26300 non-null float64\n",
+ " 9 ewTotVal 26301 non-null int64 \n",
+ " 10 ewUsdVal 26300 non-null float64\n",
+ " 11 ewTotCnt 26301 non-null int64 \n",
+ " 12 ewUsdCnt 26300 non-null float64\n",
+ " 13 sprtrn 15981 non-null float64\n",
+ " 14 spindx 15982 non-null float64\n",
+ "dtypes: float64(10), int64(4), str(1)\n",
+ "memory usage: 3.0 MB\n"
+ ]
+ }
+ ],
+ "source": [
+ "crsp.info()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "88ce7182",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:07.884334Z",
+ "iopub.status.busy": "2026-10-09T06:33:07.883511Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.132986Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.128879Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | count | \n",
+ " 26300.000000 | \n",
+ " 26300.000000 | \n",
+ " 2.630100e+04 | \n",
+ " 2.630000e+04 | \n",
+ " 26301.000000 | \n",
+ " 26300.000000 | \n",
+ " 26300.000000 | \n",
+ " 26300.000000 | \n",
+ " 2.630100e+04 | \n",
+ " 2.630000e+04 | \n",
+ " 26301.000000 | \n",
+ " 26300.000000 | \n",
+ " 15981.000000 | \n",
+ " 15982.000000 | \n",
+ "
\n",
+ " \n",
+ " | mean | \n",
+ " 0.000421 | \n",
+ " 0.000286 | \n",
+ " 8.463483e+09 | \n",
+ " 8.459652e+09 | \n",
+ " 3935.620661 | \n",
+ " 3930.434487 | \n",
+ " 0.000801 | \n",
+ " 0.000689 | \n",
+ " 8.699635e+09 | \n",
+ " 8.695712e+09 | \n",
+ " 4075.014980 | \n",
+ " 4071.904411 | \n",
+ " 0.000355 | \n",
+ " 1088.306449 | \n",
+ "
\n",
+ " \n",
+ " | std | \n",
+ " 0.010710 | \n",
+ " 0.010709 | \n",
+ " 1.555537e+10 | \n",
+ " 1.554715e+10 | \n",
+ " 2899.110650 | \n",
+ " 2896.441375 | \n",
+ " 0.010570 | \n",
+ " 0.010572 | \n",
+ " 1.593272e+10 | \n",
+ " 1.592440e+10 | \n",
+ " 3042.168464 | \n",
+ " 3041.323725 | \n",
+ " 0.010357 | \n",
+ " 1371.250067 | \n",
+ "
\n",
+ " \n",
+ " | min | \n",
+ " -0.171345 | \n",
+ " -0.171419 | \n",
+ " 1.229773e+07 | \n",
+ " 1.228914e+07 | \n",
+ " 406.000000 | \n",
+ " 404.000000 | \n",
+ " -0.135468 | \n",
+ " -0.135510 | \n",
+ " 1.243940e+07 | \n",
+ " 1.243080e+07 | \n",
+ " 408.000000 | \n",
+ " 406.000000 | \n",
+ " -0.204669 | \n",
+ " 53.490000 | \n",
+ "
\n",
+ " \n",
+ " | 25% | \n",
+ " -0.003854 | \n",
+ " -0.003980 | \n",
+ " 6.339168e+07 | \n",
+ " 6.330839e+07 | \n",
+ " 944.000000 | \n",
+ " 943.000000 | \n",
+ " -0.003011 | \n",
+ " -0.003138 | \n",
+ " 6.372042e+07 | \n",
+ " 6.365784e+07 | \n",
+ " 947.000000 | \n",
+ " 946.000000 | \n",
+ " -0.004274 | \n",
+ " 106.325000 | \n",
+ "
\n",
+ " \n",
+ " | 50% | \n",
+ " 0.000759 | \n",
+ " 0.000624 | \n",
+ " 7.730611e+08 | \n",
+ " 7.728701e+08 | \n",
+ " 4753.000000 | \n",
+ " 4747.000000 | \n",
+ " 0.001280 | \n",
+ " 0.001172 | \n",
+ " 7.956396e+08 | \n",
+ " 7.954800e+08 | \n",
+ " 4827.000000 | \n",
+ " 4821.000000 | \n",
+ " 0.000485 | \n",
+ " 460.845000 | \n",
+ "
\n",
+ " \n",
+ " | 75% | \n",
+ " 0.005075 | \n",
+ " 0.004952 | \n",
+ " 1.204819e+10 | \n",
+ " 1.204109e+10 | \n",
+ " 6630.000000 | \n",
+ " 6608.000000 | \n",
+ " 0.005063 | \n",
+ " 0.004956 | \n",
+ " 1.237183e+10 | \n",
+ " 1.237003e+10 | \n",
+ " 6876.000000 | \n",
+ " 6872.000000 | \n",
+ " 0.005240 | \n",
+ " 1376.532500 | \n",
+ "
\n",
+ " \n",
+ " | max | \n",
+ " 0.156838 | \n",
+ " 0.152974 | \n",
+ " 8.856812e+10 | \n",
+ " 8.856811e+10 | \n",
+ " 9166.000000 | \n",
+ " 9163.000000 | \n",
+ " 0.203020 | \n",
+ " 0.201795 | \n",
+ " 9.014111e+10 | \n",
+ " 9.014109e+10 | \n",
+ " 9538.000000 | \n",
+ " 9535.000000 | \n",
+ " 0.115800 | \n",
+ " 6932.050000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "count 26300.000000 26300.000000 2.630100e+04 2.630000e+04 26301.000000 \n",
+ "mean 0.000421 0.000286 8.463483e+09 8.459652e+09 3935.620661 \n",
+ "std 0.010710 0.010709 1.555537e+10 1.554715e+10 2899.110650 \n",
+ "min -0.171345 -0.171419 1.229773e+07 1.228914e+07 406.000000 \n",
+ "25% -0.003854 -0.003980 6.339168e+07 6.330839e+07 944.000000 \n",
+ "50% 0.000759 0.000624 7.730611e+08 7.728701e+08 4753.000000 \n",
+ "75% 0.005075 0.004952 1.204819e+10 1.204109e+10 6630.000000 \n",
+ "max 0.156838 0.152974 8.856812e+10 8.856811e+10 9166.000000 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal \\\n",
+ "count 26300.000000 26300.000000 26300.000000 2.630100e+04 2.630000e+04 \n",
+ "mean 3930.434487 0.000801 0.000689 8.699635e+09 8.695712e+09 \n",
+ "std 2896.441375 0.010570 0.010572 1.593272e+10 1.592440e+10 \n",
+ "min 404.000000 -0.135468 -0.135510 1.243940e+07 1.243080e+07 \n",
+ "25% 943.000000 -0.003011 -0.003138 6.372042e+07 6.365784e+07 \n",
+ "50% 4747.000000 0.001280 0.001172 7.956396e+08 7.954800e+08 \n",
+ "75% 6608.000000 0.005063 0.004956 1.237183e+10 1.237003e+10 \n",
+ "max 9163.000000 0.203020 0.201795 9.014111e+10 9.014109e+10 \n",
+ "\n",
+ " ewTotCnt ewUsdCnt sprtrn spindx \n",
+ "count 26301.000000 26300.000000 15981.000000 15982.000000 \n",
+ "mean 4075.014980 4071.904411 0.000355 1088.306449 \n",
+ "std 3042.168464 3041.323725 0.010357 1371.250067 \n",
+ "min 408.000000 406.000000 -0.204669 53.490000 \n",
+ "25% 947.000000 946.000000 -0.004274 106.325000 \n",
+ "50% 4827.000000 4821.000000 0.000485 460.845000 \n",
+ "75% 6876.000000 6872.000000 0.005240 1376.532500 \n",
+ "max 9538.000000 9535.000000 0.115800 6932.050000 "
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.describe()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "2d1829d6",
+ "metadata": {},
+ "source": [
+ "6. 选择列\n",
+ "\n",
+ "① 单层中括号取出 `sprtrn` 列(Series);② 双层中括号同时取出 `DlyCalDt` 和 `sprtrn` 两列(DataFrame),并用 `type()` 验证。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "c2987c6e",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.145930Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.144341Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.167788Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.163775Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "pandas.Series"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "sprtrn_series = crsp['sprtrn']\n",
+ "type(sprtrn_series)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "5400dfa7",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.179336Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.177948Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.209012Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.201637Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "pandas.DataFrame"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp_two_cols = crsp[['DlyCalDt', 'sprtrn']]\n",
+ "type(crsp_two_cols)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "167e98ea",
+ "metadata": {},
+ "source": [
+ "7. 选择行\n",
+ "\n",
+ "① 用 `iloc` 选出第 0 行到第 4 行、第 0 列到第 2 列;② 用 `at` 取出第 1 行 `vwretd` 列的数值;③ 用 `loc` 选出第 0 行到第 4 行、且只包含 `DlyCalDt` 和 `vwretd` 两列。`iloc` 按整数位置切片(含头不含尾),`loc` 按标签切片(首尾都包含)。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "1cb98b32",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.219493Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.218344Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.265945Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.260243Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx\n",
+ "0 1925-12-31 NaN NaN\n",
+ "1 1926-01-02 0.005689 0.005689\n",
+ "2 1926-01-04 0.000706 0.000706\n",
+ "3 1926-01-05 -0.004821 -0.004867\n",
+ "4 1926-01-06 -0.000423 -0.000427"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.iloc[0:5, 0:3]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "1b786edb",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.275398Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.274390Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.297639Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.292013Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.005689"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.at[1, 'vwretd']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "8491dd67",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.307638Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.306948Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.341062Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.337752Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd\n",
+ "0 1925-12-31 NaN\n",
+ "1 1926-01-02 0.005689\n",
+ "2 1926-01-04 0.000706\n",
+ "3 1926-01-05 -0.004821\n",
+ "4 1926-01-06 -0.000423"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp.loc[0:4, ['DlyCalDt', 'vwretd']]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d98287b2",
+ "metadata": {},
+ "source": [
+ "8. 日期处理三步曲\n",
+ "\n",
+ "① 把 `DlyCalDt` 列从文本转换为 `datetime` 格式;② 按 `DlyCalDt` 升序排序;③ 把 `DlyCalDt` 设为索引。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "4db3b33e",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.353840Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.352809Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.479765Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.474097Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 2.736676e+07 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 2.742462e+07 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 2.747972e+07 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 2.753802e+07 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 2.756176e+07 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 2.762038e+07 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 2.752684e+07 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 2.758518e+07 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 26296 | \n",
+ " 2025-12-24 | \n",
+ " 0.002914 | \n",
+ " 0.002904 | \n",
+ " 88568121481 | \n",
+ " 8.831774e+10 | \n",
+ " 9126 | \n",
+ " 9126.0 | \n",
+ " 0.003368 | \n",
+ " 0.003125 | \n",
+ " 90141105180 | \n",
+ " 8.988752e+10 | \n",
+ " 9498 | \n",
+ " 9498.0 | \n",
+ " 0.003221 | \n",
+ " 6932.05 | \n",
+ "
\n",
+ " \n",
+ " | 26297 | \n",
+ " 2025-12-26 | \n",
+ " -0.000242 | \n",
+ " -0.000325 | \n",
+ " 88542581122 | \n",
+ " 8.856811e+10 | \n",
+ " 9124 | \n",
+ " 9124.0 | \n",
+ " -0.002105 | \n",
+ " -0.002373 | \n",
+ " 90125553062 | \n",
+ " 9.014109e+10 | \n",
+ " 9496 | \n",
+ " 9496.0 | \n",
+ " -0.000304 | \n",
+ " 6929.94 | \n",
+ "
\n",
+ " \n",
+ " | 26298 | \n",
+ " 2025-12-29 | \n",
+ " -0.004191 | \n",
+ " -0.004230 | \n",
+ " 88169518843 | \n",
+ " 8.854242e+10 | \n",
+ " 9123 | \n",
+ " 9123.0 | \n",
+ " -0.008373 | \n",
+ " -0.008603 | \n",
+ " 89739994612 | \n",
+ " 9.012539e+10 | \n",
+ " 9495 | \n",
+ " 9495.0 | \n",
+ " -0.003492 | \n",
+ " 6905.74 | \n",
+ "
\n",
+ " \n",
+ " | 26299 | \n",
+ " 2025-12-30 | \n",
+ " -0.001550 | \n",
+ " -0.001576 | \n",
+ " 88028533719 | \n",
+ " 8.816264e+10 | \n",
+ " 9132 | \n",
+ " 9121.0 | \n",
+ " -0.002831 | \n",
+ " -0.003547 | \n",
+ " 89596162338 | \n",
+ " 8.973311e+10 | \n",
+ " 9504 | \n",
+ " 9493.0 | \n",
+ " -0.001376 | \n",
+ " 6896.24 | \n",
+ "
\n",
+ " \n",
+ " | 26300 | \n",
+ " 2025-12-31 | \n",
+ " -0.007319 | \n",
+ " -0.007491 | \n",
+ " 87552025121 | \n",
+ " 8.802809e+10 | \n",
+ " 9134 | \n",
+ " 9131.0 | \n",
+ " -0.005245 | \n",
+ " -0.005627 | \n",
+ " 89118194675 | \n",
+ " 8.959572e+10 | \n",
+ " 9506 | \n",
+ " 9503.0 | \n",
+ " -0.007358 | \n",
+ " 6845.50 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
26301 rows × 15 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "0 1925-12-31 NaN NaN 27487487 NaN 500 \n",
+ "1 1926-01-02 0.005689 0.005689 27600297 2.736676e+07 494 \n",
+ "2 1926-01-04 0.000706 0.000706 27577892 2.747972e+07 499 \n",
+ "3 1926-01-05 -0.004821 -0.004867 27530213 2.756176e+07 498 \n",
+ "4 1926-01-06 -0.000423 -0.000427 27618773 2.752684e+07 502 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 2025-12-24 0.002914 0.002904 88568121481 8.831774e+10 9126 \n",
+ "26297 2025-12-26 -0.000242 -0.000325 88542581122 8.856811e+10 9124 \n",
+ "26298 2025-12-29 -0.004191 -0.004230 88169518843 8.854242e+10 9123 \n",
+ "26299 2025-12-30 -0.001550 -0.001576 88028533719 8.816264e+10 9132 \n",
+ "26300 2025-12-31 -0.007319 -0.007491 87552025121 8.802809e+10 9134 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal ewTotCnt \\\n",
+ "0 NaN NaN NaN 27545352 NaN 503 \n",
+ "1 491.0 0.009516 0.009516 27658600 2.742462e+07 497 \n",
+ "2 492.0 0.005780 0.005780 27636515 2.753802e+07 502 \n",
+ "3 496.0 -0.001927 -0.002030 27588552 2.762038e+07 501 \n",
+ "4 497.0 0.001182 0.001155 27676674 2.758518e+07 505 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 9126.0 0.003368 0.003125 90141105180 8.988752e+10 9498 \n",
+ "26297 9124.0 -0.002105 -0.002373 90125553062 9.014109e+10 9496 \n",
+ "26298 9123.0 -0.008373 -0.008603 89739994612 9.012539e+10 9495 \n",
+ "26299 9121.0 -0.002831 -0.003547 89596162338 8.973311e+10 9504 \n",
+ "26300 9131.0 -0.005245 -0.005627 89118194675 8.959572e+10 9506 \n",
+ "\n",
+ " ewUsdCnt sprtrn spindx \n",
+ "0 NaN NaN NaN \n",
+ "1 494.0 NaN NaN \n",
+ "2 495.0 NaN NaN \n",
+ "3 499.0 NaN NaN \n",
+ "4 500.0 NaN NaN \n",
+ "... ... ... ... \n",
+ "26296 9498.0 0.003221 6932.05 \n",
+ "26297 9496.0 -0.000304 6929.94 \n",
+ "26298 9495.0 -0.003492 6905.74 \n",
+ "26299 9493.0 -0.001376 6896.24 \n",
+ "26300 9503.0 -0.007358 6845.50 \n",
+ "\n",
+ "[26301 rows x 15 columns]"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp['DlyCalDt'] = pd.to_datetime(crsp['DlyCalDt'], format='%Y-%m-%d')\n",
+ "crsp"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "fe827242",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.490641Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.489043Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.604629Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.602560Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 2.736676e+07 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 2.742462e+07 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 2.747972e+07 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 2.753802e+07 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 2.756176e+07 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 2.762038e+07 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 2.752684e+07 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 2.758518e+07 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 26296 | \n",
+ " 2025-12-24 | \n",
+ " 0.002914 | \n",
+ " 0.002904 | \n",
+ " 88568121481 | \n",
+ " 8.831774e+10 | \n",
+ " 9126 | \n",
+ " 9126.0 | \n",
+ " 0.003368 | \n",
+ " 0.003125 | \n",
+ " 90141105180 | \n",
+ " 8.988752e+10 | \n",
+ " 9498 | \n",
+ " 9498.0 | \n",
+ " 0.003221 | \n",
+ " 6932.05 | \n",
+ "
\n",
+ " \n",
+ " | 26297 | \n",
+ " 2025-12-26 | \n",
+ " -0.000242 | \n",
+ " -0.000325 | \n",
+ " 88542581122 | \n",
+ " 8.856811e+10 | \n",
+ " 9124 | \n",
+ " 9124.0 | \n",
+ " -0.002105 | \n",
+ " -0.002373 | \n",
+ " 90125553062 | \n",
+ " 9.014109e+10 | \n",
+ " 9496 | \n",
+ " 9496.0 | \n",
+ " -0.000304 | \n",
+ " 6929.94 | \n",
+ "
\n",
+ " \n",
+ " | 26298 | \n",
+ " 2025-12-29 | \n",
+ " -0.004191 | \n",
+ " -0.004230 | \n",
+ " 88169518843 | \n",
+ " 8.854242e+10 | \n",
+ " 9123 | \n",
+ " 9123.0 | \n",
+ " -0.008373 | \n",
+ " -0.008603 | \n",
+ " 89739994612 | \n",
+ " 9.012539e+10 | \n",
+ " 9495 | \n",
+ " 9495.0 | \n",
+ " -0.003492 | \n",
+ " 6905.74 | \n",
+ "
\n",
+ " \n",
+ " | 26299 | \n",
+ " 2025-12-30 | \n",
+ " -0.001550 | \n",
+ " -0.001576 | \n",
+ " 88028533719 | \n",
+ " 8.816264e+10 | \n",
+ " 9132 | \n",
+ " 9121.0 | \n",
+ " -0.002831 | \n",
+ " -0.003547 | \n",
+ " 89596162338 | \n",
+ " 8.973311e+10 | \n",
+ " 9504 | \n",
+ " 9493.0 | \n",
+ " -0.001376 | \n",
+ " 6896.24 | \n",
+ "
\n",
+ " \n",
+ " | 26300 | \n",
+ " 2025-12-31 | \n",
+ " -0.007319 | \n",
+ " -0.007491 | \n",
+ " 87552025121 | \n",
+ " 8.802809e+10 | \n",
+ " 9134 | \n",
+ " 9131.0 | \n",
+ " -0.005245 | \n",
+ " -0.005627 | \n",
+ " 89118194675 | \n",
+ " 8.959572e+10 | \n",
+ " 9506 | \n",
+ " 9503.0 | \n",
+ " -0.007358 | \n",
+ " 6845.50 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
26301 rows × 15 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "0 1925-12-31 NaN NaN 27487487 NaN 500 \n",
+ "1 1926-01-02 0.005689 0.005689 27600297 2.736676e+07 494 \n",
+ "2 1926-01-04 0.000706 0.000706 27577892 2.747972e+07 499 \n",
+ "3 1926-01-05 -0.004821 -0.004867 27530213 2.756176e+07 498 \n",
+ "4 1926-01-06 -0.000423 -0.000427 27618773 2.752684e+07 502 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 2025-12-24 0.002914 0.002904 88568121481 8.831774e+10 9126 \n",
+ "26297 2025-12-26 -0.000242 -0.000325 88542581122 8.856811e+10 9124 \n",
+ "26298 2025-12-29 -0.004191 -0.004230 88169518843 8.854242e+10 9123 \n",
+ "26299 2025-12-30 -0.001550 -0.001576 88028533719 8.816264e+10 9132 \n",
+ "26300 2025-12-31 -0.007319 -0.007491 87552025121 8.802809e+10 9134 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal ewTotCnt \\\n",
+ "0 NaN NaN NaN 27545352 NaN 503 \n",
+ "1 491.0 0.009516 0.009516 27658600 2.742462e+07 497 \n",
+ "2 492.0 0.005780 0.005780 27636515 2.753802e+07 502 \n",
+ "3 496.0 -0.001927 -0.002030 27588552 2.762038e+07 501 \n",
+ "4 497.0 0.001182 0.001155 27676674 2.758518e+07 505 \n",
+ "... ... ... ... ... ... ... \n",
+ "26296 9126.0 0.003368 0.003125 90141105180 8.988752e+10 9498 \n",
+ "26297 9124.0 -0.002105 -0.002373 90125553062 9.014109e+10 9496 \n",
+ "26298 9123.0 -0.008373 -0.008603 89739994612 9.012539e+10 9495 \n",
+ "26299 9121.0 -0.002831 -0.003547 89596162338 8.973311e+10 9504 \n",
+ "26300 9131.0 -0.005245 -0.005627 89118194675 8.959572e+10 9506 \n",
+ "\n",
+ " ewUsdCnt sprtrn spindx \n",
+ "0 NaN NaN NaN \n",
+ "1 494.0 NaN NaN \n",
+ "2 495.0 NaN NaN \n",
+ "3 499.0 NaN NaN \n",
+ "4 500.0 NaN NaN \n",
+ "... ... ... ... \n",
+ "26296 9498.0 0.003221 6932.05 \n",
+ "26297 9496.0 -0.000304 6929.94 \n",
+ "26298 9495.0 -0.003492 6905.74 \n",
+ "26299 9493.0 -0.001376 6896.24 \n",
+ "26300 9503.0 -0.007358 6845.50 \n",
+ "\n",
+ "[26301 rows x 15 columns]"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp = crsp.sort_values('DlyCalDt')\n",
+ "crsp"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "40905fae",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.620836Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.617668Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.744412Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.739711Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " | DlyCalDt | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 1925-12-31 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27487487 | \n",
+ " NaN | \n",
+ " 500 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 27545352 | \n",
+ " NaN | \n",
+ " 503 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1926-01-02 | \n",
+ " 0.005689 | \n",
+ " 0.005689 | \n",
+ " 27600297 | \n",
+ " 2.736676e+07 | \n",
+ " 494 | \n",
+ " 491.0 | \n",
+ " 0.009516 | \n",
+ " 0.009516 | \n",
+ " 27658600 | \n",
+ " 2.742462e+07 | \n",
+ " 497 | \n",
+ " 494.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1926-01-04 | \n",
+ " 0.000706 | \n",
+ " 0.000706 | \n",
+ " 27577892 | \n",
+ " 2.747972e+07 | \n",
+ " 499 | \n",
+ " 492.0 | \n",
+ " 0.005780 | \n",
+ " 0.005780 | \n",
+ " 27636515 | \n",
+ " 2.753802e+07 | \n",
+ " 502 | \n",
+ " 495.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1926-01-05 | \n",
+ " -0.004821 | \n",
+ " -0.004867 | \n",
+ " 27530213 | \n",
+ " 2.756176e+07 | \n",
+ " 498 | \n",
+ " 496.0 | \n",
+ " -0.001927 | \n",
+ " -0.002030 | \n",
+ " 27588552 | \n",
+ " 2.762038e+07 | \n",
+ " 501 | \n",
+ " 499.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1926-01-06 | \n",
+ " -0.000423 | \n",
+ " -0.000427 | \n",
+ " 27618773 | \n",
+ " 2.752684e+07 | \n",
+ " 502 | \n",
+ " 497.0 | \n",
+ " 0.001182 | \n",
+ " 0.001155 | \n",
+ " 27676674 | \n",
+ " 2.758518e+07 | \n",
+ " 505 | \n",
+ " 500.0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 2025-12-24 | \n",
+ " 0.002914 | \n",
+ " 0.002904 | \n",
+ " 88568121481 | \n",
+ " 8.831774e+10 | \n",
+ " 9126 | \n",
+ " 9126.0 | \n",
+ " 0.003368 | \n",
+ " 0.003125 | \n",
+ " 90141105180 | \n",
+ " 8.988752e+10 | \n",
+ " 9498 | \n",
+ " 9498.0 | \n",
+ " 0.003221 | \n",
+ " 6932.05 | \n",
+ "
\n",
+ " \n",
+ " | 2025-12-26 | \n",
+ " -0.000242 | \n",
+ " -0.000325 | \n",
+ " 88542581122 | \n",
+ " 8.856811e+10 | \n",
+ " 9124 | \n",
+ " 9124.0 | \n",
+ " -0.002105 | \n",
+ " -0.002373 | \n",
+ " 90125553062 | \n",
+ " 9.014109e+10 | \n",
+ " 9496 | \n",
+ " 9496.0 | \n",
+ " -0.000304 | \n",
+ " 6929.94 | \n",
+ "
\n",
+ " \n",
+ " | 2025-12-29 | \n",
+ " -0.004191 | \n",
+ " -0.004230 | \n",
+ " 88169518843 | \n",
+ " 8.854242e+10 | \n",
+ " 9123 | \n",
+ " 9123.0 | \n",
+ " -0.008373 | \n",
+ " -0.008603 | \n",
+ " 89739994612 | \n",
+ " 9.012539e+10 | \n",
+ " 9495 | \n",
+ " 9495.0 | \n",
+ " -0.003492 | \n",
+ " 6905.74 | \n",
+ "
\n",
+ " \n",
+ " | 2025-12-30 | \n",
+ " -0.001550 | \n",
+ " -0.001576 | \n",
+ " 88028533719 | \n",
+ " 8.816264e+10 | \n",
+ " 9132 | \n",
+ " 9121.0 | \n",
+ " -0.002831 | \n",
+ " -0.003547 | \n",
+ " 89596162338 | \n",
+ " 8.973311e+10 | \n",
+ " 9504 | \n",
+ " 9493.0 | \n",
+ " -0.001376 | \n",
+ " 6896.24 | \n",
+ "
\n",
+ " \n",
+ " | 2025-12-31 | \n",
+ " -0.007319 | \n",
+ " -0.007491 | \n",
+ " 87552025121 | \n",
+ " 8.802809e+10 | \n",
+ " 9134 | \n",
+ " 9131.0 | \n",
+ " -0.005245 | \n",
+ " -0.005627 | \n",
+ " 89118194675 | \n",
+ " 8.959572e+10 | \n",
+ " 9506 | \n",
+ " 9503.0 | \n",
+ " -0.007358 | \n",
+ " 6845.50 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
26301 rows × 14 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " vwretd vwretx vwTotVal vwUsdVal vwTotCnt vwUsdCnt \\\n",
+ "DlyCalDt \n",
+ "1925-12-31 NaN NaN 27487487 NaN 500 NaN \n",
+ "1926-01-02 0.005689 0.005689 27600297 2.736676e+07 494 491.0 \n",
+ "1926-01-04 0.000706 0.000706 27577892 2.747972e+07 499 492.0 \n",
+ "1926-01-05 -0.004821 -0.004867 27530213 2.756176e+07 498 496.0 \n",
+ "1926-01-06 -0.000423 -0.000427 27618773 2.752684e+07 502 497.0 \n",
+ "... ... ... ... ... ... ... \n",
+ "2025-12-24 0.002914 0.002904 88568121481 8.831774e+10 9126 9126.0 \n",
+ "2025-12-26 -0.000242 -0.000325 88542581122 8.856811e+10 9124 9124.0 \n",
+ "2025-12-29 -0.004191 -0.004230 88169518843 8.854242e+10 9123 9123.0 \n",
+ "2025-12-30 -0.001550 -0.001576 88028533719 8.816264e+10 9132 9121.0 \n",
+ "2025-12-31 -0.007319 -0.007491 87552025121 8.802809e+10 9134 9131.0 \n",
+ "\n",
+ " ewretd ewretx ewTotVal ewUsdVal ewTotCnt ewUsdCnt \\\n",
+ "DlyCalDt \n",
+ "1925-12-31 NaN NaN 27545352 NaN 503 NaN \n",
+ "1926-01-02 0.009516 0.009516 27658600 2.742462e+07 497 494.0 \n",
+ "1926-01-04 0.005780 0.005780 27636515 2.753802e+07 502 495.0 \n",
+ "1926-01-05 -0.001927 -0.002030 27588552 2.762038e+07 501 499.0 \n",
+ "1926-01-06 0.001182 0.001155 27676674 2.758518e+07 505 500.0 \n",
+ "... ... ... ... ... ... ... \n",
+ "2025-12-24 0.003368 0.003125 90141105180 8.988752e+10 9498 9498.0 \n",
+ "2025-12-26 -0.002105 -0.002373 90125553062 9.014109e+10 9496 9496.0 \n",
+ "2025-12-29 -0.008373 -0.008603 89739994612 9.012539e+10 9495 9495.0 \n",
+ "2025-12-30 -0.002831 -0.003547 89596162338 8.973311e+10 9504 9493.0 \n",
+ "2025-12-31 -0.005245 -0.005627 89118194675 8.959572e+10 9506 9503.0 \n",
+ "\n",
+ " sprtrn spindx \n",
+ "DlyCalDt \n",
+ "1925-12-31 NaN NaN \n",
+ "1926-01-02 NaN NaN \n",
+ "1926-01-04 NaN NaN \n",
+ "1926-01-05 NaN NaN \n",
+ "1926-01-06 NaN NaN \n",
+ "... ... ... \n",
+ "2025-12-24 0.003221 6932.05 \n",
+ "2025-12-26 -0.000304 6929.94 \n",
+ "2025-12-29 -0.003492 6905.74 \n",
+ "2025-12-30 -0.001376 6896.24 \n",
+ "2025-12-31 -0.007358 6845.50 \n",
+ "\n",
+ "[26301 rows x 14 columns]"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp = crsp.set_index('DlyCalDt')\n",
+ "crsp"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "875abb6e",
+ "metadata": {},
+ "source": [
+ "9. 按时间筛选\n",
+ "\n",
+ "筛选出 2020 年全年的数据,赋值给 `crsp_2020`,并检查行数(大约 253 个交易日)。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "745aacd5",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.752993Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.751983Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.864520Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.862526Z"
+ }
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "253\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " | DlyCalDt | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 2020-01-02 | \n",
+ " 0.007412 | \n",
+ " 0.007316 | \n",
+ " 41464754137 | \n",
+ " 4.115634e+10 | \n",
+ " 6871 | \n",
+ " 6866.0 | \n",
+ " 0.005470 | \n",
+ " 0.005428 | \n",
+ " 42902996443 | \n",
+ " 4.255570e+10 | \n",
+ " 7253 | \n",
+ " 7248.0 | \n",
+ " 0.008379 | \n",
+ " 3257.85 | \n",
+ "
\n",
+ " \n",
+ " | 2020-01-03 | \n",
+ " -0.005828 | \n",
+ " -0.005900 | \n",
+ " 41221078749 | \n",
+ " 4.146475e+10 | \n",
+ " 6871 | \n",
+ " 6871.0 | \n",
+ " -0.003057 | \n",
+ " -0.003072 | \n",
+ " 42645264616 | \n",
+ " 4.290300e+10 | \n",
+ " 7253 | \n",
+ " 7253.0 | \n",
+ " -0.007060 | \n",
+ " 3234.85 | \n",
+ "
\n",
+ " \n",
+ " | 2020-01-06 | \n",
+ " 0.003269 | \n",
+ " 0.003245 | \n",
+ " 41345986288 | \n",
+ " 4.121183e+10 | \n",
+ " 6871 | \n",
+ " 6869.0 | \n",
+ " 0.004548 | \n",
+ " 0.004519 | \n",
+ " 42768514163 | \n",
+ " 4.263602e+10 | \n",
+ " 7253 | \n",
+ " 7251.0 | \n",
+ " 0.003533 | \n",
+ " 3246.28 | \n",
+ "
\n",
+ " \n",
+ " | 2020-01-07 | \n",
+ " -0.002147 | \n",
+ " -0.002216 | \n",
+ " 41255461753 | \n",
+ " 4.134598e+10 | \n",
+ " 6870 | \n",
+ " 6870.0 | \n",
+ " -0.000041 | \n",
+ " -0.000057 | \n",
+ " 42699866212 | \n",
+ " 4.276851e+10 | \n",
+ " 7253 | \n",
+ " 7252.0 | \n",
+ " -0.002803 | \n",
+ " 3237.18 | \n",
+ "
\n",
+ " \n",
+ " | 2020-01-08 | \n",
+ " 0.004028 | \n",
+ " 0.003996 | \n",
+ " 41421675525 | \n",
+ " 4.125546e+10 | \n",
+ " 6871 | \n",
+ " 6870.0 | \n",
+ " 0.000914 | \n",
+ " 0.000903 | \n",
+ " 42870237688 | \n",
+ " 4.269987e+10 | \n",
+ " 7254 | \n",
+ " 7253.0 | \n",
+ " 0.004902 | \n",
+ " 3253.05 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 2020-12-24 | \n",
+ " 0.002330 | \n",
+ " 0.002195 | \n",
+ " 49379202924 | \n",
+ " 4.929405e+10 | \n",
+ " 7101 | \n",
+ " 7101.0 | \n",
+ " -0.000277 | \n",
+ " -0.000458 | \n",
+ " 50948672283 | \n",
+ " 5.091918e+10 | \n",
+ " 7515 | \n",
+ " 7515.0 | \n",
+ " 0.003537 | \n",
+ " 3703.06 | \n",
+ "
\n",
+ " \n",
+ " | 2020-12-28 | \n",
+ " 0.003847 | \n",
+ " 0.003836 | \n",
+ " 49569832981 | \n",
+ " 4.937920e+10 | \n",
+ " 7103 | \n",
+ " 7101.0 | \n",
+ " 0.001350 | \n",
+ " 0.001304 | \n",
+ " 51120836691 | \n",
+ " 5.093776e+10 | \n",
+ " 7516 | \n",
+ " 7514.0 | \n",
+ " 0.008723 | \n",
+ " 3735.36 | \n",
+ "
\n",
+ " \n",
+ " | 2020-12-29 | \n",
+ " -0.003652 | \n",
+ " -0.003660 | \n",
+ " 49387356377 | \n",
+ " 4.956717e+10 | \n",
+ " 7108 | \n",
+ " 7101.0 | \n",
+ " -0.008483 | \n",
+ " -0.008656 | \n",
+ " 50978120468 | \n",
+ " 5.111818e+10 | \n",
+ " 7522 | \n",
+ " 7514.0 | \n",
+ " -0.002227 | \n",
+ " 3727.04 | \n",
+ "
\n",
+ " \n",
+ " | 2020-12-30 | \n",
+ " 0.003291 | \n",
+ " 0.003124 | \n",
+ " 49542217608 | \n",
+ " 4.938705e+10 | \n",
+ " 7107 | \n",
+ " 7105.0 | \n",
+ " 0.010155 | \n",
+ " 0.009754 | \n",
+ " 51166821544 | \n",
+ " 5.097782e+10 | \n",
+ " 7521 | \n",
+ " 7519.0 | \n",
+ " 0.001342 | \n",
+ " 3732.04 | \n",
+ "
\n",
+ " \n",
+ " | 2020-12-31 | \n",
+ " 0.003558 | \n",
+ " 0.003499 | \n",
+ " 49839515298 | \n",
+ " 4.954190e+10 | \n",
+ " 7111 | \n",
+ " 7105.0 | \n",
+ " -0.001058 | \n",
+ " -0.001129 | \n",
+ " 51464416577 | \n",
+ " 5.116650e+10 | \n",
+ " 7525 | \n",
+ " 7519.0 | \n",
+ " 0.006439 | \n",
+ " 3756.07 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
253 rows × 14 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " vwretd vwretx vwTotVal vwUsdVal vwTotCnt vwUsdCnt \\\n",
+ "DlyCalDt \n",
+ "2020-01-02 0.007412 0.007316 41464754137 4.115634e+10 6871 6866.0 \n",
+ "2020-01-03 -0.005828 -0.005900 41221078749 4.146475e+10 6871 6871.0 \n",
+ "2020-01-06 0.003269 0.003245 41345986288 4.121183e+10 6871 6869.0 \n",
+ "2020-01-07 -0.002147 -0.002216 41255461753 4.134598e+10 6870 6870.0 \n",
+ "2020-01-08 0.004028 0.003996 41421675525 4.125546e+10 6871 6870.0 \n",
+ "... ... ... ... ... ... ... \n",
+ "2020-12-24 0.002330 0.002195 49379202924 4.929405e+10 7101 7101.0 \n",
+ "2020-12-28 0.003847 0.003836 49569832981 4.937920e+10 7103 7101.0 \n",
+ "2020-12-29 -0.003652 -0.003660 49387356377 4.956717e+10 7108 7101.0 \n",
+ "2020-12-30 0.003291 0.003124 49542217608 4.938705e+10 7107 7105.0 \n",
+ "2020-12-31 0.003558 0.003499 49839515298 4.954190e+10 7111 7105.0 \n",
+ "\n",
+ " ewretd ewretx ewTotVal ewUsdVal ewTotCnt ewUsdCnt \\\n",
+ "DlyCalDt \n",
+ "2020-01-02 0.005470 0.005428 42902996443 4.255570e+10 7253 7248.0 \n",
+ "2020-01-03 -0.003057 -0.003072 42645264616 4.290300e+10 7253 7253.0 \n",
+ "2020-01-06 0.004548 0.004519 42768514163 4.263602e+10 7253 7251.0 \n",
+ "2020-01-07 -0.000041 -0.000057 42699866212 4.276851e+10 7253 7252.0 \n",
+ "2020-01-08 0.000914 0.000903 42870237688 4.269987e+10 7254 7253.0 \n",
+ "... ... ... ... ... ... ... \n",
+ "2020-12-24 -0.000277 -0.000458 50948672283 5.091918e+10 7515 7515.0 \n",
+ "2020-12-28 0.001350 0.001304 51120836691 5.093776e+10 7516 7514.0 \n",
+ "2020-12-29 -0.008483 -0.008656 50978120468 5.111818e+10 7522 7514.0 \n",
+ "2020-12-30 0.010155 0.009754 51166821544 5.097782e+10 7521 7519.0 \n",
+ "2020-12-31 -0.001058 -0.001129 51464416577 5.116650e+10 7525 7519.0 \n",
+ "\n",
+ " sprtrn spindx \n",
+ "DlyCalDt \n",
+ "2020-01-02 0.008379 3257.85 \n",
+ "2020-01-03 -0.007060 3234.85 \n",
+ "2020-01-06 0.003533 3246.28 \n",
+ "2020-01-07 -0.002803 3237.18 \n",
+ "2020-01-08 0.004902 3253.05 \n",
+ "... ... ... \n",
+ "2020-12-24 0.003537 3703.06 \n",
+ "2020-12-28 0.008723 3735.36 \n",
+ "2020-12-29 -0.002227 3727.04 \n",
+ "2020-12-30 0.001342 3732.04 \n",
+ "2020-12-31 0.006439 3756.07 \n",
+ "\n",
+ "[253 rows x 14 columns]"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "crsp_2020 = crsp.loc['2020']\n",
+ "print(len(crsp_2020))\n",
+ "crsp_2020"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "630c5b57",
+ "metadata": {},
+ "source": [
+ "10. 保存数据\n",
+ "\n",
+ "把 `crsp_2020` 保存为 `datasets/CRSP_2020.csv`:① 把日期索引一并写入文件(`index=True`);② 用 `encoding='utf-8-sig'`,Excel 直接打开不出现乱码。保存后重新读回验证。"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "bffe7661",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.874430Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.873649Z",
+ "iopub.status.idle": "2026-10-09T06:33:08.904051Z",
+ "shell.execute_reply": "2026-10-09T06:33:08.900808Z"
+ }
+ },
+ "outputs": [],
+ "source": [
+ "crsp_2020.to_csv('datasets/CRSP_2020.csv', index=True, encoding='utf-8-sig')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "82797d15",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-10-09T06:33:08.914592Z",
+ "iopub.status.busy": "2026-10-09T06:33:08.911383Z",
+ "iopub.status.idle": "2026-10-09T06:33:09.031226Z",
+ "shell.execute_reply": "2026-10-09T06:33:09.027079Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DlyCalDt | \n",
+ " vwretd | \n",
+ " vwretx | \n",
+ " vwTotVal | \n",
+ " vwUsdVal | \n",
+ " vwTotCnt | \n",
+ " vwUsdCnt | \n",
+ " ewretd | \n",
+ " ewretx | \n",
+ " ewTotVal | \n",
+ " ewUsdVal | \n",
+ " ewTotCnt | \n",
+ " ewUsdCnt | \n",
+ " sprtrn | \n",
+ " spindx | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 2020-01-02 | \n",
+ " 0.007412 | \n",
+ " 0.007316 | \n",
+ " 41464754137 | \n",
+ " 4.115634e+10 | \n",
+ " 6871 | \n",
+ " 6866.0 | \n",
+ " 0.005470 | \n",
+ " 0.005428 | \n",
+ " 42902996443 | \n",
+ " 4.255570e+10 | \n",
+ " 7253 | \n",
+ " 7248.0 | \n",
+ " 0.008379 | \n",
+ " 3257.85 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 2020-01-03 | \n",
+ " -0.005828 | \n",
+ " -0.005900 | \n",
+ " 41221078749 | \n",
+ " 4.146475e+10 | \n",
+ " 6871 | \n",
+ " 6871.0 | \n",
+ " -0.003057 | \n",
+ " -0.003072 | \n",
+ " 42645264616 | \n",
+ " 4.290300e+10 | \n",
+ " 7253 | \n",
+ " 7253.0 | \n",
+ " -0.007060 | \n",
+ " 3234.85 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 2020-01-06 | \n",
+ " 0.003269 | \n",
+ " 0.003245 | \n",
+ " 41345986288 | \n",
+ " 4.121183e+10 | \n",
+ " 6871 | \n",
+ " 6869.0 | \n",
+ " 0.004548 | \n",
+ " 0.004519 | \n",
+ " 42768514163 | \n",
+ " 4.263602e+10 | \n",
+ " 7253 | \n",
+ " 7251.0 | \n",
+ " 0.003533 | \n",
+ " 3246.28 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 2020-01-07 | \n",
+ " -0.002147 | \n",
+ " -0.002216 | \n",
+ " 41255461753 | \n",
+ " 4.134598e+10 | \n",
+ " 6870 | \n",
+ " 6870.0 | \n",
+ " -0.000041 | \n",
+ " -0.000057 | \n",
+ " 42699866212 | \n",
+ " 4.276851e+10 | \n",
+ " 7253 | \n",
+ " 7252.0 | \n",
+ " -0.002803 | \n",
+ " 3237.18 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 2020-01-08 | \n",
+ " 0.004028 | \n",
+ " 0.003996 | \n",
+ " 41421675525 | \n",
+ " 4.125546e+10 | \n",
+ " 6871 | \n",
+ " 6870.0 | \n",
+ " 0.000914 | \n",
+ " 0.000903 | \n",
+ " 42870237688 | \n",
+ " 4.269987e+10 | \n",
+ " 7254 | \n",
+ " 7253.0 | \n",
+ " 0.004902 | \n",
+ " 3253.05 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 248 | \n",
+ " 2020-12-24 | \n",
+ " 0.002330 | \n",
+ " 0.002195 | \n",
+ " 49379202924 | \n",
+ " 4.929405e+10 | \n",
+ " 7101 | \n",
+ " 7101.0 | \n",
+ " -0.000277 | \n",
+ " -0.000458 | \n",
+ " 50948672283 | \n",
+ " 5.091918e+10 | \n",
+ " 7515 | \n",
+ " 7515.0 | \n",
+ " 0.003537 | \n",
+ " 3703.06 | \n",
+ "
\n",
+ " \n",
+ " | 249 | \n",
+ " 2020-12-28 | \n",
+ " 0.003847 | \n",
+ " 0.003836 | \n",
+ " 49569832981 | \n",
+ " 4.937920e+10 | \n",
+ " 7103 | \n",
+ " 7101.0 | \n",
+ " 0.001350 | \n",
+ " 0.001304 | \n",
+ " 51120836691 | \n",
+ " 5.093776e+10 | \n",
+ " 7516 | \n",
+ " 7514.0 | \n",
+ " 0.008723 | \n",
+ " 3735.36 | \n",
+ "
\n",
+ " \n",
+ " | 250 | \n",
+ " 2020-12-29 | \n",
+ " -0.003652 | \n",
+ " -0.003660 | \n",
+ " 49387356377 | \n",
+ " 4.956717e+10 | \n",
+ " 7108 | \n",
+ " 7101.0 | \n",
+ " -0.008483 | \n",
+ " -0.008656 | \n",
+ " 50978120468 | \n",
+ " 5.111818e+10 | \n",
+ " 7522 | \n",
+ " 7514.0 | \n",
+ " -0.002227 | \n",
+ " 3727.04 | \n",
+ "
\n",
+ " \n",
+ " | 251 | \n",
+ " 2020-12-30 | \n",
+ " 0.003291 | \n",
+ " 0.003124 | \n",
+ " 49542217608 | \n",
+ " 4.938705e+10 | \n",
+ " 7107 | \n",
+ " 7105.0 | \n",
+ " 0.010155 | \n",
+ " 0.009754 | \n",
+ " 51166821544 | \n",
+ " 5.097782e+10 | \n",
+ " 7521 | \n",
+ " 7519.0 | \n",
+ " 0.001342 | \n",
+ " 3732.04 | \n",
+ "
\n",
+ " \n",
+ " | 252 | \n",
+ " 2020-12-31 | \n",
+ " 0.003558 | \n",
+ " 0.003499 | \n",
+ " 49839515298 | \n",
+ " 4.954190e+10 | \n",
+ " 7111 | \n",
+ " 7105.0 | \n",
+ " -0.001058 | \n",
+ " -0.001129 | \n",
+ " 51464416577 | \n",
+ " 5.116650e+10 | \n",
+ " 7525 | \n",
+ " 7519.0 | \n",
+ " 0.006439 | \n",
+ " 3756.07 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
253 rows × 15 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " DlyCalDt vwretd vwretx vwTotVal vwUsdVal vwTotCnt \\\n",
+ "0 2020-01-02 0.007412 0.007316 41464754137 4.115634e+10 6871 \n",
+ "1 2020-01-03 -0.005828 -0.005900 41221078749 4.146475e+10 6871 \n",
+ "2 2020-01-06 0.003269 0.003245 41345986288 4.121183e+10 6871 \n",
+ "3 2020-01-07 -0.002147 -0.002216 41255461753 4.134598e+10 6870 \n",
+ "4 2020-01-08 0.004028 0.003996 41421675525 4.125546e+10 6871 \n",
+ ".. ... ... ... ... ... ... \n",
+ "248 2020-12-24 0.002330 0.002195 49379202924 4.929405e+10 7101 \n",
+ "249 2020-12-28 0.003847 0.003836 49569832981 4.937920e+10 7103 \n",
+ "250 2020-12-29 -0.003652 -0.003660 49387356377 4.956717e+10 7108 \n",
+ "251 2020-12-30 0.003291 0.003124 49542217608 4.938705e+10 7107 \n",
+ "252 2020-12-31 0.003558 0.003499 49839515298 4.954190e+10 7111 \n",
+ "\n",
+ " vwUsdCnt ewretd ewretx ewTotVal ewUsdVal ewTotCnt \\\n",
+ "0 6866.0 0.005470 0.005428 42902996443 4.255570e+10 7253 \n",
+ "1 6871.0 -0.003057 -0.003072 42645264616 4.290300e+10 7253 \n",
+ "2 6869.0 0.004548 0.004519 42768514163 4.263602e+10 7253 \n",
+ "3 6870.0 -0.000041 -0.000057 42699866212 4.276851e+10 7253 \n",
+ "4 6870.0 0.000914 0.000903 42870237688 4.269987e+10 7254 \n",
+ ".. ... ... ... ... ... ... \n",
+ "248 7101.0 -0.000277 -0.000458 50948672283 5.091918e+10 7515 \n",
+ "249 7101.0 0.001350 0.001304 51120836691 5.093776e+10 7516 \n",
+ "250 7101.0 -0.008483 -0.008656 50978120468 5.111818e+10 7522 \n",
+ "251 7105.0 0.010155 0.009754 51166821544 5.097782e+10 7521 \n",
+ "252 7105.0 -0.001058 -0.001129 51464416577 5.116650e+10 7525 \n",
+ "\n",
+ " ewUsdCnt sprtrn spindx \n",
+ "0 7248.0 0.008379 3257.85 \n",
+ "1 7253.0 -0.007060 3234.85 \n",
+ "2 7251.0 0.003533 3246.28 \n",
+ "3 7252.0 -0.002803 3237.18 \n",
+ "4 7253.0 0.004902 3253.05 \n",
+ ".. ... ... ... \n",
+ "248 7515.0 0.003537 3703.06 \n",
+ "249 7514.0 0.008723 3735.36 \n",
+ "250 7514.0 -0.002227 3727.04 \n",
+ "251 7519.0 0.001342 3732.04 \n",
+ "252 7519.0 0.006439 3756.07 \n",
+ "\n",
+ "[253 rows x 15 columns]"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "check = pd.read_csv('datasets/CRSP_2020.csv')\n",
+ "check"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3.11 (jupyter)",
+ "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": "3.11.16"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}