midterm project update

JuliaIron · Sep 6, 2021 · 2281b6a · 2281b6a
1 parent 4ee6bb5
commit 2281b6a
Showing 1 changed file with 32 additions and 30 deletions.
diff --git a/Connect Python_MySQL-D.ipynb b/Connect Python_MySQL-D.ipynb
@@ -83,7 +83,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fd2da802",
+   "id": "695d1a9f",
    "metadata": {},
    "source": [
     "Inspect the Data Base"
@@ -100141,7 +100141,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "8b8e1dff",
+   "id": "9a01ee48",
    "metadata": {},
    "outputs": [
     {
@@ -100279,7 +100279,7 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "id": "f065e8a7",
+   "id": "996252de",
    "metadata": {},
    "outputs": [
     {
@@ -100416,7 +100416,7 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "id": "09884db8",
+   "id": "c57f1f62",
    "metadata": {},
    "outputs": [
     {
@@ -100516,7 +100516,7 @@
   {
    "cell_type": "code",
    "execution_count": 25,
-   "id": "0ca2cd8d",
+   "id": "deccdcfb",
    "metadata": {},
    "outputs": [
     {
@@ -100622,7 +100622,7 @@
   {
    "cell_type": "code",
    "execution_count": 28,
-   "id": "457af3fd",
+   "id": "243a7aba",
    "metadata": {},
    "outputs": [
     {
@@ -100746,20 +100746,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
-   "id": "31611c8d",
+   "execution_count": null,
+   "id": "f8fb5bfb",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# query8 = \"SELECT * olist.order_items JOIN olist.order_status_year_price ON order_item_id\"\n",
+    "# query8 = \"select * from olist.order_items inner join olist.order_status_year_price on olist.order_items.order_item_id\"\n",
     "# res_df = pd.read_sql_query(query8, db_connection)\n",
     "# res_df.head()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 51,
-   "id": "ca02e3f6",
+   "id": "55e42743",
    "metadata": {},
    "outputs": [
     {
@@ -100865,7 +100865,7 @@
   {
    "cell_type": "code",
    "execution_count": 54,
-   "id": "59fd5502",
+   "id": "f8292c07",
    "metadata": {},
    "outputs": [
     {
@@ -100995,7 +100995,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8fc7b14a",
+   "id": "0991b4ef",
    "metadata": {},
    "source": [
     "### Data exploration"
@@ -101004,7 +101004,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "id": "2956ef12",
+   "id": "bdc90223",
    "metadata": {},
    "outputs": [
     {
@@ -101027,7 +101027,7 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "id": "cfac4819",
+   "id": "38fe57b2",
    "metadata": {},
    "outputs": [
     {
@@ -101048,7 +101048,7 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "id": "dc2268f5",
+   "id": "8337af02",
    "metadata": {},
    "outputs": [
     {
@@ -101069,7 +101069,7 @@
   {
    "cell_type": "code",
    "execution_count": 29,
-   "id": "2fe8f647",
+   "id": "be67f1ea",
    "metadata": {},
    "outputs": [
     {
@@ -101090,7 +101090,7 @@
   {
    "cell_type": "code",
    "execution_count": 55,
-   "id": "d30a6203",
+   "id": "52c99399",
    "metadata": {},
    "outputs": [
     {
@@ -101111,7 +101111,7 @@
   {
    "cell_type": "code",
    "execution_count": 56,
-   "id": "471e0cfc",
+   "id": "a2dbc70c",
    "metadata": {},
    "outputs": [
     {
@@ -101132,7 +101132,7 @@
   {
    "cell_type": "code",
    "execution_count": 35,
-   "id": "cda20df7",
+   "id": "cefdc59c",
    "metadata": {},
    "outputs": [
     {
@@ -101153,7 +101153,7 @@
   {
    "cell_type": "code",
    "execution_count": 38,
-   "id": "b63018f5",
+   "id": "026c7343",
    "metadata": {},
    "outputs": [
     {
@@ -101174,7 +101174,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6f71fc7f",
+   "id": "ead6fe4b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101184,7 +101184,7 @@
   {
    "cell_type": "code",
    "execution_count": 77,
-   "id": "a796e709",
+   "id": "5ed21e41",
    "metadata": {},
    "outputs": [
     {
@@ -101213,7 +101213,7 @@
   {
    "cell_type": "code",
    "execution_count": 78,
-   "id": "be8f7039",
+   "id": "83f47ac6",
    "metadata": {},
    "outputs": [
     {
@@ -101242,7 +101242,7 @@
   {
    "cell_type": "code",
    "execution_count": 79,
-   "id": "0271cb2d",
+   "id": "f6ab0605",
    "metadata": {},
    "outputs": [
     {
@@ -101271,7 +101271,7 @@
   {
    "cell_type": "code",
    "execution_count": 80,
-   "id": "ac8d3124",
+   "id": "5ca5e138",
    "metadata": {},
    "outputs": [
     {
@@ -101300,7 +101300,7 @@
   {
    "cell_type": "code",
    "execution_count": 36,
-   "id": "c098908b",
+   "id": "2b132eb3",
    "metadata": {},
    "outputs": [
     {
@@ -101321,7 +101321,7 @@
   {
    "cell_type": "code",
    "execution_count": 39,
-   "id": "09cd1275",
+   "id": "1eb9a2fc",
    "metadata": {},
    "outputs": [
     {
@@ -101342,7 +101342,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f94b5920",
+   "id": "82c50770",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101351,7 +101351,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ccf39e09",
+   "id": "a26e6f38",
    "metadata": {},
    "source": [
     "### Data cleaning pipeline"
@@ -101360,11 +101360,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f69c99db",
+   "id": "9c206851",
    "metadata": {},
    "outputs": [],
    "source": [
     "def data_cleaning(df):\n",
+    "    fillna(value=mean_xx)\n",
+    "\n",
     "    df = df.dropna()\n",
     "    \n",
     "    \n",