Move FRED saves to DATA_DIR

jmbejara · Aug 6, 2024 · 8619051 · 8619051
1 parent 0af2b54
commit 8619051
Show file tree

Hide file tree

Showing 3 changed files with 25 additions and 11,884 deletions.
diff --git a/src/03_factor_analysis_demo.ipynb b/src/03_factor_analysis_demo.ipynb
@@ -41,6 +41,16 @@
     "import statsmodels.multivariate.pca"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import config\n",
+    "DATA_DIR = config.DATA_DIR"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -112,7 +122,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.to_csv('fred_panel.csv')"
+    "df.to_csv(DATA_DIR / 'fred_panel.csv')"
    ]
   },
   {
@@ -121,7 +131,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dff = pd.read_csv('fred_panel.csv')"
+    "dff = pd.read_csv(DATA_DIR / 'fred_panel.csv')"
    ]
   },
   {
@@ -139,7 +149,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dff = pd.read_csv('fred_panel.csv', parse_dates=['DATE'])"
+    "dff = pd.read_csv(DATA_DIR / 'fred_panel.csv', parse_dates=['DATE'])"
    ]
   },
   {
@@ -166,7 +176,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.to_parquet('fred_panel.parquet')"
+    "df.to_parquet(DATA_DIR / 'fred_panel.parquet')"
    ]
   },
   {
@@ -175,7 +185,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pd.read_parquet('fred_panel.parquet')"
+    "df = pd.read_parquet(DATA_DIR / 'fred_panel.parquet')"
    ]
   },
   {
@@ -624,7 +634,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = yf.download(\" \".join(tickers), start=\"1980-01-01\", end=\"2023-08-01\")"
+    "data = yf.download(\" \".join(tickers), start=\"1980-01-01\", end=\"2024-08-01\", progress=False)"
    ]
   },
   {
@@ -662,6 +672,15 @@
     "df = df.drop(columns=cols_with_many_nas).dropna().pct_change().dropna()\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.columns"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,