diff --git a/sum23/lecture_materials/20_Databases/lec_20_database3_notes.ipynb b/sum23/lecture_materials/20_Databases/lec_20_database3_notes.ipynb
index fdcc3ea64e8b40eb2d4b3fe684864160fe0d8dab..71ac70831a00e41e1a0c38d11c33ba3744240551 100644
--- a/sum23/lecture_materials/20_Databases/lec_20_database3_notes.ipynb
+++ b/sum23/lecture_materials/20_Databases/lec_20_database3_notes.ipynb
@@ -27,7 +27,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -38,7 +38,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
@@ -48,7 +48,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -63,7 +63,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -135,7 +135,7 @@
"2 CREATE TABLE \"species\" (\\n\"code\" TEXT,\\n \"spe... "
]
},
- "execution_count": 6,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -146,7 +146,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
@@ -158,7 +158,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -249,7 +249,7 @@
"4 E 50 4 m 12 99"
]
},
- "execution_count": 8,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -268,7 +268,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -317,7 +317,7 @@
"1 p pine"
]
},
- "execution_count": 9,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -330,7 +330,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -431,7 +431,7 @@
"5 2018 blue Pacer public 1109 1"
]
},
- "execution_count": 10,
+ "execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -457,21 +457,135 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 12,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "1 B 20 4 m 10 100\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "#trees[trees[\"priority\"] > 90] "
+ "trees[trees[\"priority\"] > 90] "
]
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 13,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x y\n",
+ "1 20 4\n",
+ "4 50 4"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# DataFrame with Boolean Indexing # show only the columns in this list\n",
- "#trees[trees[\"priority\"] > 90] [[\"x\", \"y\"]] "
+ "trees[trees[\"priority\"] > 90] [[\"x\", \"y\"]] "
]
},
{
@@ -483,7 +597,7 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 14,
"metadata": {},
"outputs": [
{
@@ -574,7 +688,7 @@
"4 E 50 4 m 12 99"
]
},
- "execution_count": 15,
+ "execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@@ -585,7 +699,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 15,
"metadata": {},
"outputs": [
{
@@ -634,19 +748,18 @@
"1 50 4"
]
},
- "execution_count": 17,
+ "execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# your answer here\n",
- "query = \"\"\"\n",
- " SELECT x, y\n",
+ "qry(\"\"\"\n",
+ " SELECT x,y\n",
" FROM trees\n",
" WHERE priority > 90\n",
- "\"\"\"\n",
- "qry(query)"
+ "\"\"\")"
]
},
{
@@ -659,16 +772,109 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 16,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"trees"
]
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
@@ -719,7 +925,7 @@
"2 54"
]
},
- "execution_count": 18,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@@ -732,12 +938,12 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "### 2b. *Convert* the query into an equivalent *pandas* statement."
+ "### 2b. *Convert* the querry into an equivalent *pandas* statement."
]
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -751,7 +957,7 @@
"Name: x, dtype: int64"
]
},
- "execution_count": 19,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -763,7 +969,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 19,
"metadata": {},
"outputs": [
{
@@ -775,7 +981,7 @@
"Name: x, dtype: int64"
]
},
- "execution_count": 20,
+ "execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
@@ -787,7 +993,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 20,
"metadata": {},
"outputs": [
{
@@ -799,19 +1005,19 @@
"Name: y, dtype: int64"
]
},
- "execution_count": 21,
+ "execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Do the same for y \n",
- "trees[\"y\"] [ trees[\"species\"] == 'm']"
+ "trees[\"y\"] [trees[\"species\"] == 'm']"
]
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 21,
"metadata": {},
"outputs": [
{
@@ -823,7 +1029,7 @@
"dtype: int64"
]
},
- "execution_count": 22,
+ "execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
@@ -836,7 +1042,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -887,7 +1093,7 @@
"4 54"
]
},
- "execution_count": 23,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -909,67 +1115,16 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>code</th>\n",
- " <th>species</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>m</td>\n",
- " <td>maple</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>p</td>\n",
- " <td>pine</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " code species\n",
- "0 m maple\n",
- "1 p pine"
- ]
- },
- "execution_count": 24,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"species"
]
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
@@ -978,7 +1133,7 @@
"'m'"
]
},
- "execution_count": 25,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -989,7 +1144,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -1000,7 +1155,7 @@
"Name: code, dtype: object"
]
},
- "execution_count": 29,
+ "execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
@@ -1012,7 +1167,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 26,
"metadata": {},
"outputs": [
{
@@ -1022,7 +1177,7 @@
"Name: code, dtype: object"
]
},
- "execution_count": 30,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -1034,7 +1189,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -1043,7 +1198,7 @@
"'m'"
]
},
- "execution_count": 31,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -1055,7 +1210,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 28,
"metadata": {},
"outputs": [
{
@@ -1064,7 +1219,7 @@
"'m'"
]
},
- "execution_count": 32,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -1076,7 +1231,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 29,
"metadata": {},
"outputs": [
{
@@ -1128,24 +1283,6 @@
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
- " <td>C</td>\n",
- " <td>30</td>\n",
- " <td>4</td>\n",
- " <td>p</td>\n",
- " <td>6</td>\n",
- " <td>30</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>D</td>\n",
- " <td>40</td>\n",
- " <td>4</td>\n",
- " <td>p</td>\n",
- " <td>8</td>\n",
- " <td>40</td>\n",
- " </tr>\n",
- " <tr>\n",
" <th>4</th>\n",
" <td>E</td>\n",
" <td>50</td>\n",
@@ -1162,24 +1299,22 @@
" tree x y species diameter priority\n",
"0 A 10 4 m 8 71\n",
"1 B 20 4 m 10 100\n",
- "2 C 30 4 p 6 30\n",
- "3 D 40 4 p 8 40\n",
"4 E 50 4 m 12 99"
]
},
- "execution_count": 33,
+ "execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# DataFrame with Boolean Indexing\n",
- "trees"
+ "trees [trees[\"species\"] == cd]"
]
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 30,
"metadata": {},
"outputs": [
{
@@ -1191,7 +1326,7 @@
"Name: tree, dtype: object"
]
},
- "execution_count": 34,
+ "execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
@@ -1217,7 +1352,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 31,
"metadata": {},
"outputs": [
{
@@ -1258,7 +1393,7 @@
"0 m"
]
},
- "execution_count": 35,
+ "execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
@@ -1269,7 +1404,7 @@
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 32,
"metadata": {},
"outputs": [
{
@@ -1279,7 +1414,7 @@
"Name: code, dtype: object"
]
},
- "execution_count": 36,
+ "execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
@@ -1291,7 +1426,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 33,
"metadata": {},
"outputs": [
{
@@ -1300,21 +1435,21 @@
"'m'"
]
},
- "execution_count": 37,
+ "execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# DataFrame with column selection get the value at iloc 0\n",
- "cd = qry(\"select code from species where species = 'maple' \") ['code'] .iloc[0]\n",
+ "cd = qry(\"select code from species where species = 'maple' \") ['code'] .iloc[0]\n",
"cd\n",
"\n"
]
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 34,
"metadata": {},
"outputs": [
{
@@ -1365,7 +1500,7 @@
"2 E"
]
},
- "execution_count": 38,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -1377,7 +1512,7 @@
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -1428,7 +1563,7 @@
"2 E"
]
},
- "execution_count": 39,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -1448,7 +1583,7 @@
},
{
"cell_type": "code",
- "execution_count": 40,
+ "execution_count": 38,
"metadata": {},
"outputs": [
{
@@ -1509,7 +1644,7 @@
"4 p"
]
},
- "execution_count": 40,
+ "execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
@@ -1525,40 +1660,6 @@
"### 4.b *Convert* the query code to *Pandas*"
]
},
- {
- "cell_type": "code",
- "execution_count": 42,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "1 m\n",
- "4 m\n",
- "0 m\n",
- "3 p\n",
- "2 p\n",
- "Name: species, dtype: object"
- ]
- },
- "execution_count": 42,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# DataFrame soted by priority # with column selection\n",
- "trees.sort_values(\"priority\", ascending = False) ['species']"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "----\n",
- "### 5a. *Predict* the output of the following code"
- ]
- },
{
"cell_type": "code",
"execution_count": 43,
@@ -1585,71 +1686,41 @@
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
- " <th>tree</th>\n",
- " <th>x</th>\n",
- " <th>y</th>\n",
" <th>species</th>\n",
- " <th>diameter</th>\n",
- " <th>priority</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
- " <th>0</th>\n",
- " <td>A</td>\n",
- " <td>10</td>\n",
- " <td>4</td>\n",
+ " <th>1</th>\n",
" <td>m</td>\n",
- " <td>8</td>\n",
- " <td>71</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>1</th>\n",
- " <td>B</td>\n",
- " <td>20</td>\n",
- " <td>4</td>\n",
+ " <th>4</th>\n",
" <td>m</td>\n",
- " <td>10</td>\n",
- " <td>100</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
- " <td>C</td>\n",
- " <td>30</td>\n",
- " <td>4</td>\n",
- " <td>p</td>\n",
- " <td>6</td>\n",
- " <td>30</td>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
- " <td>D</td>\n",
- " <td>40</td>\n",
- " <td>4</td>\n",
" <td>p</td>\n",
- " <td>8</td>\n",
- " <td>40</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
- " <td>E</td>\n",
- " <td>50</td>\n",
- " <td>4</td>\n",
- " <td>m</td>\n",
- " <td>12</td>\n",
- " <td>99</td>\n",
+ " <th>2</th>\n",
+ " <td>p</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
- " tree x y species diameter priority\n",
- "0 A 10 4 m 8 71\n",
- "1 B 20 4 m 10 100\n",
- "2 C 30 4 p 6 30\n",
- "3 D 40 4 p 8 40\n",
- "4 E 50 4 m 12 99"
+ " species\n",
+ "1 m\n",
+ "4 m\n",
+ "0 m\n",
+ "3 p\n",
+ "2 p"
]
},
"execution_count": 43,
@@ -1657,6 +1728,24 @@
"output_type": "execute_result"
}
],
+ "source": [
+ "# DataFrame sorted by priority # with column selection\n",
+ "trees[['species','priority']].sort_values(by= 'priority', ascending=False)[['species']]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 5a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"trees"
]
@@ -1916,7 +2005,7 @@
},
{
"cell_type": "code",
- "execution_count": 50,
+ "execution_count": 51,
"metadata": {},
"outputs": [
{
@@ -1927,19 +2016,19 @@
"Name: 1, dtype: object"
]
},
- "execution_count": 50,
+ "execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "# DataFrame # grab the first row #slicing by certain indices\n",
- "trees.sort_values(\"priority\", ascending=False) .iloc[0] [[\"tree\", \"priority\"]]"
+ "# DataFrame # grab the first row #slicing by certain indices\n",
+ "trees.sort_values(\"priority\", ascending=False).iloc[0][[\"tree\",\"priority\"]]"
]
},
{
"cell_type": "code",
- "execution_count": 51,
+ "execution_count": 52,
"metadata": {},
"outputs": [
{
@@ -1948,14 +2037,14 @@
"['B', 100]"
]
},
- "execution_count": 51,
+ "execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# list gets the values only\n",
- "list(trees.sort_values(\"priority\", ascending=False) .iloc[0] [[\"tree\", \"priority\"]])"
+ "list(trees.sort_values(\"priority\", ascending=False).iloc[0][[\"tree\",\"priority\"]])"
]
},
{
@@ -1968,7 +2057,7 @@
},
{
"cell_type": "code",
- "execution_count": 54,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -2042,7 +2131,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 54,
"metadata": {},
"outputs": [
{
@@ -2051,7 +2140,7 @@
"5"
]
},
- "execution_count": 55,
+ "execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
@@ -2064,7 +2153,7 @@
},
{
"cell_type": "code",
- "execution_count": 57,
+ "execution_count": 55,
"metadata": {},
"outputs": [
{
@@ -2075,7 +2164,7 @@
"Name: species, dtype: int64"
]
},
- "execution_count": 57,
+ "execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
@@ -2087,7 +2176,7 @@
},
{
"cell_type": "code",
- "execution_count": 58,
+ "execution_count": 56,
"metadata": {},
"outputs": [
{
@@ -2096,19 +2185,19 @@
"2"
]
},
- "execution_count": 58,
+ "execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "c2 = len(trees['species'].value_counts())\n",
+ "c2 = len( trees['species'].value_counts() )\n",
"c2"
]
},
{
"cell_type": "code",
- "execution_count": 59,
+ "execution_count": 57,
"metadata": {},
"outputs": [
{
@@ -2117,7 +2206,7 @@
"[5, 2]"
]
},
- "execution_count": 59,
+ "execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
@@ -2129,7 +2218,7 @@
},
{
"cell_type": "code",
- "execution_count": 60,
+ "execution_count": 58,
"metadata": {},
"outputs": [
{
@@ -2172,7 +2261,7 @@
"0 5 2"
]
},
- "execution_count": 60,
+ "execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
@@ -2205,7 +2294,109 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 59,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
"metadata": {},
"outputs": [
{
@@ -2257,7 +2448,7 @@
"1 p 2 7.0"
]
},
- "execution_count": 61,
+ "execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
@@ -2278,7 +2469,7 @@
},
{
"cell_type": "code",
- "execution_count": 62,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
@@ -2287,7 +2478,7 @@
"['m', 'p']"
]
},
- "execution_count": 62,
+ "execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
@@ -2300,14 +2491,14 @@
},
{
"cell_type": "code",
- "execution_count": 63,
+ "execution_count": 62,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "/var/folders/07/v8h5vw9j6v71xlj9rgbrh5h40000gn/T/ipykernel_17964/363807400.py:1: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
+ "/var/folders/07/v8h5vw9j6v71xlj9rgbrh5h40000gn/T/ipykernel_22914/363807400.py:1: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
" trees.groupby(\"species\").mean()\n"
]
},
@@ -2371,7 +2562,7 @@
"p 35.000000 4.0 7.0 35.0"
]
},
- "execution_count": 63,
+ "execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
@@ -2382,14 +2573,14 @@
},
{
"cell_type": "code",
- "execution_count": 64,
+ "execution_count": 63,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "/var/folders/07/v8h5vw9j6v71xlj9rgbrh5h40000gn/T/ipykernel_17964/3042628405.py:2: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
+ "/var/folders/07/v8h5vw9j6v71xlj9rgbrh5h40000gn/T/ipykernel_22914/3042628405.py:2: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
" size_list = list(trees.groupby(\"species\").mean()[\"diameter\"])\n"
]
},
@@ -2399,7 +2590,7 @@
"[10.0, 7.0]"
]
},
- "execution_count": 64,
+ "execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
@@ -2412,7 +2603,7 @@
},
{
"cell_type": "code",
- "execution_count": 65,
+ "execution_count": 64,
"metadata": {},
"outputs": [
{
@@ -2421,7 +2612,7 @@
"[3, 2]"
]
},
- "execution_count": 65,
+ "execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
@@ -2434,7 +2625,7 @@
},
{
"cell_type": "code",
- "execution_count": 66,
+ "execution_count": 65,
"metadata": {},
"outputs": [
{
@@ -2486,7 +2677,7 @@
"1 p 2 7.0"
]
},
- "execution_count": 66,
+ "execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
@@ -2498,6 +2689,15 @@
" \"size\": size_list})"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "conn.close()"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
diff --git a/sum23/lecture_materials/21_Advanced_Pandas/lec_21_pandas3_data_transformation_notes.ipynb b/sum23/lecture_materials/21_Advanced_Pandas/lec_21_pandas3_data_transformation_notes.ipynb
index 2a9fa0eef8be35cf2cffa26b0621ba420fbe4a31..aa9b274768af69ea352e49760cd763a9e6c0dc6b 100644
--- a/sum23/lecture_materials/21_Advanced_Pandas/lec_21_pandas3_data_transformation_notes.ipynb
+++ b/sum23/lecture_materials/21_Advanced_Pandas/lec_21_pandas3_data_transformation_notes.ipynb
@@ -179,7 +179,7 @@
}
],
"source": [
- "df = qry(\"SELECT * from sqlite_master\")\n",
+ "df = qry(\"SELECT * FROM sqlite_master\")\n",
"df"
]
},
@@ -192,7 +192,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -233,7 +233,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -565,13 +565,13 @@
"[35877 rows x 17 columns]"
]
},
- "execution_count": 7,
+ "execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df = qry(\"SELECT * from spotify\")\n",
+ "df = qry(\"SELECT * FROM spotify\")\n",
"df"
]
},
@@ -588,7 +588,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -924,7 +924,7 @@
"[35877 rows x 16 columns]"
]
},
- "execution_count": 9,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -955,7 +955,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -1265,7 +1265,7 @@
"6xEnbXM1us9fDJy2LC0lru -5.431 0.0895 0.0797 "
]
},
- "execution_count": 10,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -1289,7 +1289,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1316,7 +1316,7 @@
"Name: song_name, Length: 35877, dtype: bool"
]
},
- "execution_count": 12,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -1336,7 +1336,7 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1353,7 +1353,7 @@
"Name: song_name, dtype: int64"
]
},
- "execution_count": 13,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -1374,7 +1374,7 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1559,7 +1559,7 @@
" <tr>\n",
" <th>46bXU7Sgj7104ZoXxzz9tM</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>269208</td>\n",
" <td>4</td>\n",
@@ -1578,7 +1578,7 @@
" <tr>\n",
" <th>0he2ViGMUO3ajKTxLOfWVT</th>\n",
" <td>Greatest Hardstyle Playlist</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>210112</td>\n",
" <td>0</td>\n",
@@ -1597,7 +1597,7 @@
" <tr>\n",
" <th>72DAt9Lbpy9EUS29OzQLob</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>234823</td>\n",
" <td>8</td>\n",
@@ -1616,7 +1616,7 @@
" <tr>\n",
" <th>6HXgExFVuE1c3cq9QjFCcU</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>323200</td>\n",
" <td>6</td>\n",
@@ -1635,7 +1635,7 @@
" <tr>\n",
" <th>6MAAMZImxcvYhRnxDLTufD</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>162161</td>\n",
" <td>9</td>\n",
@@ -1671,77 +1671,77 @@
"6HXgExFVuE1c3cq9QjFCcU Euphoric Hardstyle \n",
"6MAAMZImxcvYhRnxDLTufD Best of Hardstyle 2020 \n",
"\n",
- " song_name genre \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p Pathology Dark Trap \n",
- "0vSWgAlfpye0WCGeNmuNhy Symbiote Dark Trap \n",
- "7EL7ifncK2PWFYThJjzR25 BRAINFOOD Dark Trap \n",
- "1umsRbM7L4ju7rn9aU8Ju6 Sacrifice Dark Trap \n",
- "4SKqOHKYU5pgHr5UiVKiQN Backpack Dark Trap \n",
- "... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM This song does not have a name hardstyle \n",
- "0he2ViGMUO3ajKTxLOfWVT This song does not have a name hardstyle \n",
- "72DAt9Lbpy9EUS29OzQLob This song does not have a name hardstyle \n",
- "6HXgExFVuE1c3cq9QjFCcU This song does not have a name hardstyle \n",
- "6MAAMZImxcvYhRnxDLTufD This song does not have a name hardstyle \n",
+ " song_name genre duration_ms \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p Pathology Dark Trap 224427 \n",
+ "0vSWgAlfpye0WCGeNmuNhy Symbiote Dark Trap 98821 \n",
+ "7EL7ifncK2PWFYThJjzR25 BRAINFOOD Dark Trap 101172 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 Sacrifice Dark Trap 96062 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN Backpack Dark Trap 135079 \n",
+ "... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM This song doesn't have a name hardstyle 269208 \n",
+ "0he2ViGMUO3ajKTxLOfWVT This song doesn't have a name hardstyle 210112 \n",
+ "72DAt9Lbpy9EUS29OzQLob This song doesn't have a name hardstyle 234823 \n",
+ "6HXgExFVuE1c3cq9QjFCcU This song doesn't have a name hardstyle 323200 \n",
+ "6MAAMZImxcvYhRnxDLTufD This song doesn't have a name hardstyle 162161 \n",
"\n",
- " duration_ms key mode time_signature tempo \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 224427 8 1 4 115.080 \n",
- "0vSWgAlfpye0WCGeNmuNhy 98821 5 1 4 218.050 \n",
- "7EL7ifncK2PWFYThJjzR25 101172 8 1 4 189.938 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 96062 10 0 4 139.990 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 135079 5 1 4 128.014 \n",
- "... ... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 269208 4 1 4 150.013 \n",
- "0he2ViGMUO3ajKTxLOfWVT 210112 0 0 4 149.928 \n",
- "72DAt9Lbpy9EUS29OzQLob 234823 8 1 4 154.935 \n",
- "6HXgExFVuE1c3cq9QjFCcU 323200 6 0 4 150.042 \n",
- "6MAAMZImxcvYhRnxDLTufD 162161 9 1 4 155.047 \n",
+ " key mode time_signature tempo acousticness \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p 8 1 4 115.080 0.401000 \n",
+ "0vSWgAlfpye0WCGeNmuNhy 5 1 4 218.050 0.013800 \n",
+ "7EL7ifncK2PWFYThJjzR25 8 1 4 189.938 0.187000 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 10 0 4 139.990 0.145000 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN 5 1 4 128.014 0.007700 \n",
+ "... ... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 4 1 4 150.013 0.031500 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0 0 4 149.928 0.022500 \n",
+ "72DAt9Lbpy9EUS29OzQLob 8 1 4 154.935 0.026000 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 6 0 4 150.042 0.000551 \n",
+ "6MAAMZImxcvYhRnxDLTufD 9 1 4 155.047 0.001890 \n",
"\n",
- " acousticness danceability energy instrumentalness \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.401000 0.719 0.493 0.000000 \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.013800 0.850 0.893 0.000004 \n",
- "7EL7ifncK2PWFYThJjzR25 0.187000 0.864 0.365 0.000000 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.145000 0.767 0.576 0.000003 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.007700 0.765 0.726 0.000000 \n",
- "... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.031500 0.528 0.693 0.000345 \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.022500 0.517 0.768 0.000018 \n",
- "72DAt9Lbpy9EUS29OzQLob 0.026000 0.361 0.821 0.000242 \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.000551 0.477 0.921 0.029600 \n",
- "6MAAMZImxcvYhRnxDLTufD 0.001890 0.529 0.945 0.000055 \n",
+ " danceability energy instrumentalness liveness \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p 0.719 0.493 0.000000 0.1180 \n",
+ "0vSWgAlfpye0WCGeNmuNhy 0.850 0.893 0.000004 0.3720 \n",
+ "7EL7ifncK2PWFYThJjzR25 0.864 0.365 0.000000 0.1160 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 0.767 0.576 0.000003 0.0968 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN 0.765 0.726 0.000000 0.6190 \n",
+ "... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 0.528 0.693 0.000345 0.1210 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0.517 0.768 0.000018 0.2050 \n",
+ "72DAt9Lbpy9EUS29OzQLob 0.361 0.821 0.000242 0.3850 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 0.477 0.921 0.029600 0.0575 \n",
+ "6MAAMZImxcvYhRnxDLTufD 0.529 0.945 0.000055 0.4140 \n",
"\n",
- " liveness loudness speechiness valence \n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.1180 -7.230 0.0794 0.1240 \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.3720 -4.783 0.0623 0.0391 \n",
- "7EL7ifncK2PWFYThJjzR25 0.1160 -10.219 0.0655 0.0478 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.0968 -9.683 0.2560 0.1870 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.6190 -5.580 0.1910 0.2700 \n",
- "... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.1210 -5.148 0.0304 0.3940 \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.2050 -7.922 0.0479 0.3830 \n",
- "72DAt9Lbpy9EUS29OzQLob 0.3850 -3.102 0.0505 0.1240 \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.0575 -4.777 0.0392 0.4880 \n",
- "6MAAMZImxcvYhRnxDLTufD 0.4140 -5.862 0.0615 0.1340 \n",
+ " loudness speechiness valence \n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p -7.230 0.0794 0.1240 \n",
+ "0vSWgAlfpye0WCGeNmuNhy -4.783 0.0623 0.0391 \n",
+ "7EL7ifncK2PWFYThJjzR25 -10.219 0.0655 0.0478 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 -9.683 0.2560 0.1870 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN -5.580 0.1910 0.2700 \n",
+ "... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM -5.148 0.0304 0.3940 \n",
+ "0he2ViGMUO3ajKTxLOfWVT -7.922 0.0479 0.3830 \n",
+ "72DAt9Lbpy9EUS29OzQLob -3.102 0.0505 0.1240 \n",
+ "6HXgExFVuE1c3cq9QjFCcU -4.777 0.0392 0.4880 \n",
+ "6MAAMZImxcvYhRnxDLTufD -5.862 0.0615 0.1340 \n",
"\n",
"[35877 rows x 16 columns]"
]
},
- "execution_count": 16,
+ "execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# use .fillna to replace missing values\n",
- "df[\"song_name\"].fillna(\"This song does not have a name\")\n",
+ "df[\"song_name\"].fillna(\"This song doesn't have a name\")\n",
"\n",
"# to replace the original DataFrame's column, you need to explicitly update that object instance\n",
"# TODO: uncomment the below lines and update the code\n",
- "df[\"song_name\"] = df[\"song_name\"].fillna(\"This song does not have a name\")\n",
+ "df[\"song_name\"] = df[\"song_name\"].fillna(\"This song doesn't have a name\")\n",
"df"
]
},
@@ -1756,7 +1756,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1828,7 +1828,7 @@
" <tr>\n",
" <th>5LzAV6KfjN8VhWCedeygfY</th>\n",
" <td>Dirtybird Players</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>techhouse</td>\n",
" <td>197499</td>\n",
" <td>7</td>\n",
@@ -1847,7 +1847,7 @@
" <tr>\n",
" <th>3TsCb6ueD678XBJDiRrvhr</th>\n",
" <td>tech house</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>techhouse</td>\n",
" <td>206000</td>\n",
" <td>10</td>\n",
@@ -1866,7 +1866,7 @@
" <tr>\n",
" <th>6Y0Fy2buEis7bEOlG0QET1</th>\n",
" <td>Tech House Bangerz</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>techhouse</td>\n",
" <td>199839</td>\n",
" <td>4</td>\n",
@@ -1885,7 +1885,7 @@
" <tr>\n",
" <th>4EJI2XGViSQp6WscLKgYDD</th>\n",
" <td>tech house</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>techhouse</td>\n",
" <td>173861</td>\n",
" <td>8</td>\n",
@@ -1904,7 +1904,7 @@
" <tr>\n",
" <th>4x6VzOQTLIrkkCWcDPh5Y0</th>\n",
" <td>blanc | Tech House</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>techhouse</td>\n",
" <td>394960</td>\n",
" <td>8</td>\n",
@@ -1942,7 +1942,7 @@
" <tr>\n",
" <th>46bXU7Sgj7104ZoXxzz9tM</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>269208</td>\n",
" <td>4</td>\n",
@@ -1961,7 +1961,7 @@
" <tr>\n",
" <th>0he2ViGMUO3ajKTxLOfWVT</th>\n",
" <td>Greatest Hardstyle Playlist</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>210112</td>\n",
" <td>0</td>\n",
@@ -1980,7 +1980,7 @@
" <tr>\n",
" <th>72DAt9Lbpy9EUS29OzQLob</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>234823</td>\n",
" <td>8</td>\n",
@@ -1999,7 +1999,7 @@
" <tr>\n",
" <th>6HXgExFVuE1c3cq9QjFCcU</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>323200</td>\n",
" <td>6</td>\n",
@@ -2018,7 +2018,7 @@
" <tr>\n",
" <th>6MAAMZImxcvYhRnxDLTufD</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>162161</td>\n",
" <td>9</td>\n",
@@ -2054,66 +2054,66 @@
"6HXgExFVuE1c3cq9QjFCcU Euphoric Hardstyle \n",
"6MAAMZImxcvYhRnxDLTufD Best of Hardstyle 2020 \n",
"\n",
- " song_name genre \\\n",
- "id \n",
- "5LzAV6KfjN8VhWCedeygfY This song does not have a name techhouse \n",
- "3TsCb6ueD678XBJDiRrvhr This song does not have a name techhouse \n",
- "6Y0Fy2buEis7bEOlG0QET1 This song does not have a name techhouse \n",
- "4EJI2XGViSQp6WscLKgYDD This song does not have a name techhouse \n",
- "4x6VzOQTLIrkkCWcDPh5Y0 This song does not have a name techhouse \n",
- "... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM This song does not have a name hardstyle \n",
- "0he2ViGMUO3ajKTxLOfWVT This song does not have a name hardstyle \n",
- "72DAt9Lbpy9EUS29OzQLob This song does not have a name hardstyle \n",
- "6HXgExFVuE1c3cq9QjFCcU This song does not have a name hardstyle \n",
- "6MAAMZImxcvYhRnxDLTufD This song does not have a name hardstyle \n",
+ " song_name genre duration_ms \\\n",
+ "id \n",
+ "5LzAV6KfjN8VhWCedeygfY This song doesn't have a name techhouse 197499 \n",
+ "3TsCb6ueD678XBJDiRrvhr This song doesn't have a name techhouse 206000 \n",
+ "6Y0Fy2buEis7bEOlG0QET1 This song doesn't have a name techhouse 199839 \n",
+ "4EJI2XGViSQp6WscLKgYDD This song doesn't have a name techhouse 173861 \n",
+ "4x6VzOQTLIrkkCWcDPh5Y0 This song doesn't have a name techhouse 394960 \n",
+ "... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM This song doesn't have a name hardstyle 269208 \n",
+ "0he2ViGMUO3ajKTxLOfWVT This song doesn't have a name hardstyle 210112 \n",
+ "72DAt9Lbpy9EUS29OzQLob This song doesn't have a name hardstyle 234823 \n",
+ "6HXgExFVuE1c3cq9QjFCcU This song doesn't have a name hardstyle 323200 \n",
+ "6MAAMZImxcvYhRnxDLTufD This song doesn't have a name hardstyle 162161 \n",
"\n",
- " duration_ms key mode time_signature tempo \\\n",
- "id \n",
- "5LzAV6KfjN8VhWCedeygfY 197499 7 1 4 127.997 \n",
- "3TsCb6ueD678XBJDiRrvhr 206000 10 1 4 124.994 \n",
- "6Y0Fy2buEis7bEOlG0QET1 199839 4 0 4 124.006 \n",
- "4EJI2XGViSQp6WscLKgYDD 173861 8 1 4 125.031 \n",
- "4x6VzOQTLIrkkCWcDPh5Y0 394960 8 0 4 127.029 \n",
- "... ... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 269208 4 1 4 150.013 \n",
- "0he2ViGMUO3ajKTxLOfWVT 210112 0 0 4 149.928 \n",
- "72DAt9Lbpy9EUS29OzQLob 234823 8 1 4 154.935 \n",
- "6HXgExFVuE1c3cq9QjFCcU 323200 6 0 4 150.042 \n",
- "6MAAMZImxcvYhRnxDLTufD 162161 9 1 4 155.047 \n",
+ " key mode time_signature tempo acousticness \\\n",
+ "id \n",
+ "5LzAV6KfjN8VhWCedeygfY 7 1 4 127.997 0.000957 \n",
+ "3TsCb6ueD678XBJDiRrvhr 10 1 4 124.994 0.062300 \n",
+ "6Y0Fy2buEis7bEOlG0QET1 4 0 4 124.006 0.019100 \n",
+ "4EJI2XGViSQp6WscLKgYDD 8 1 4 125.031 0.053000 \n",
+ "4x6VzOQTLIrkkCWcDPh5Y0 8 0 4 127.029 0.000301 \n",
+ "... ... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 4 1 4 150.013 0.031500 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0 0 4 149.928 0.022500 \n",
+ "72DAt9Lbpy9EUS29OzQLob 8 1 4 154.935 0.026000 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 6 0 4 150.042 0.000551 \n",
+ "6MAAMZImxcvYhRnxDLTufD 9 1 4 155.047 0.001890 \n",
"\n",
- " acousticness danceability energy instrumentalness \\\n",
- "id \n",
- "5LzAV6KfjN8VhWCedeygfY 0.000957 0.806 0.950 0.920000 \n",
- "3TsCb6ueD678XBJDiRrvhr 0.062300 0.729 0.978 0.908000 \n",
- "6Y0Fy2buEis7bEOlG0QET1 0.019100 0.724 0.792 0.812000 \n",
- "4EJI2XGViSQp6WscLKgYDD 0.053000 0.700 0.898 0.418000 \n",
- "4x6VzOQTLIrkkCWcDPh5Y0 0.000301 0.803 0.919 0.926000 \n",
- "... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.031500 0.528 0.693 0.000345 \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.022500 0.517 0.768 0.000018 \n",
- "72DAt9Lbpy9EUS29OzQLob 0.026000 0.361 0.821 0.000242 \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.000551 0.477 0.921 0.029600 \n",
- "6MAAMZImxcvYhRnxDLTufD 0.001890 0.529 0.945 0.000055 \n",
+ " danceability energy instrumentalness liveness \\\n",
+ "id \n",
+ "5LzAV6KfjN8VhWCedeygfY 0.806 0.950 0.920000 0.1130 \n",
+ "3TsCb6ueD678XBJDiRrvhr 0.729 0.978 0.908000 0.0353 \n",
+ "6Y0Fy2buEis7bEOlG0QET1 0.724 0.792 0.812000 0.1080 \n",
+ "4EJI2XGViSQp6WscLKgYDD 0.700 0.898 0.418000 0.5740 \n",
+ "4x6VzOQTLIrkkCWcDPh5Y0 0.803 0.919 0.926000 0.1020 \n",
+ "... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 0.528 0.693 0.000345 0.1210 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0.517 0.768 0.000018 0.2050 \n",
+ "72DAt9Lbpy9EUS29OzQLob 0.361 0.821 0.000242 0.3850 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 0.477 0.921 0.029600 0.0575 \n",
+ "6MAAMZImxcvYhRnxDLTufD 0.529 0.945 0.000055 0.4140 \n",
"\n",
- " liveness loudness speechiness valence \n",
- "id \n",
- "5LzAV6KfjN8VhWCedeygfY 0.1130 -6.782 0.0811 0.580 \n",
- "3TsCb6ueD678XBJDiRrvhr 0.0353 -6.645 0.0420 0.778 \n",
- "6Y0Fy2buEis7bEOlG0QET1 0.1080 -8.555 0.0405 0.346 \n",
- "4EJI2XGViSQp6WscLKgYDD 0.5740 -6.099 0.2570 0.791 \n",
- "4x6VzOQTLIrkkCWcDPh5Y0 0.1020 -8.667 0.0702 0.754 \n",
- "... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.1210 -5.148 0.0304 0.394 \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.2050 -7.922 0.0479 0.383 \n",
- "72DAt9Lbpy9EUS29OzQLob 0.3850 -3.102 0.0505 0.124 \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.0575 -4.777 0.0392 0.488 \n",
- "6MAAMZImxcvYhRnxDLTufD 0.4140 -5.862 0.0615 0.134 \n",
+ " loudness speechiness valence \n",
+ "id \n",
+ "5LzAV6KfjN8VhWCedeygfY -6.782 0.0811 0.580 \n",
+ "3TsCb6ueD678XBJDiRrvhr -6.645 0.0420 0.778 \n",
+ "6Y0Fy2buEis7bEOlG0QET1 -8.555 0.0405 0.346 \n",
+ "4EJI2XGViSQp6WscLKgYDD -6.099 0.2570 0.791 \n",
+ "4x6VzOQTLIrkkCWcDPh5Y0 -8.667 0.0702 0.754 \n",
+ "... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM -5.148 0.0304 0.394 \n",
+ "0he2ViGMUO3ajKTxLOfWVT -7.922 0.0479 0.383 \n",
+ "72DAt9Lbpy9EUS29OzQLob -3.102 0.0505 0.124 \n",
+ "6HXgExFVuE1c3cq9QjFCcU -4.777 0.0392 0.488 \n",
+ "6MAAMZImxcvYhRnxDLTufD -5.862 0.0615 0.134 \n",
"\n",
"[17529 rows x 16 columns]"
]
},
- "execution_count": 17,
+ "execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
@@ -2123,212 +2123,6 @@
"df.dropna()"
]
},
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>title</th>\n",
- " <th>song_name</th>\n",
- " <th>genre</th>\n",
- " <th>duration_ms</th>\n",
- " <th>key</th>\n",
- " <th>mode</th>\n",
- " <th>time_signature</th>\n",
- " <th>tempo</th>\n",
- " <th>acousticness</th>\n",
- " <th>danceability</th>\n",
- " <th>energy</th>\n",
- " <th>instrumentalness</th>\n",
- " <th>liveness</th>\n",
- " <th>loudness</th>\n",
- " <th>speechiness</th>\n",
- " <th>valence</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>id</th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>7pgJBLVz5VmnL7uGHmRj6p</th>\n",
- " <td>NaN</td>\n",
- " <td>Pathology</td>\n",
- " <td>Dark Trap</td>\n",
- " <td>224427</td>\n",
- " <td>8</td>\n",
- " <td>1</td>\n",
- " <td>4</td>\n",
- " <td>115.080</td>\n",
- " <td>0.4010</td>\n",
- " <td>0.719</td>\n",
- " <td>0.493</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.1180</td>\n",
- " <td>-7.230</td>\n",
- " <td>0.0794</td>\n",
- " <td>0.1240</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>0vSWgAlfpye0WCGeNmuNhy</th>\n",
- " <td>NaN</td>\n",
- " <td>Symbiote</td>\n",
- " <td>Dark Trap</td>\n",
- " <td>98821</td>\n",
- " <td>5</td>\n",
- " <td>1</td>\n",
- " <td>4</td>\n",
- " <td>218.050</td>\n",
- " <td>0.0138</td>\n",
- " <td>0.850</td>\n",
- " <td>0.893</td>\n",
- " <td>0.000004</td>\n",
- " <td>0.3720</td>\n",
- " <td>-4.783</td>\n",
- " <td>0.0623</td>\n",
- " <td>0.0391</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>7EL7ifncK2PWFYThJjzR25</th>\n",
- " <td>NaN</td>\n",
- " <td>BRAINFOOD</td>\n",
- " <td>Dark Trap</td>\n",
- " <td>101172</td>\n",
- " <td>8</td>\n",
- " <td>1</td>\n",
- " <td>4</td>\n",
- " <td>189.938</td>\n",
- " <td>0.1870</td>\n",
- " <td>0.864</td>\n",
- " <td>0.365</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.1160</td>\n",
- " <td>-10.219</td>\n",
- " <td>0.0655</td>\n",
- " <td>0.0478</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1umsRbM7L4ju7rn9aU8Ju6</th>\n",
- " <td>NaN</td>\n",
- " <td>Sacrifice</td>\n",
- " <td>Dark Trap</td>\n",
- " <td>96062</td>\n",
- " <td>10</td>\n",
- " <td>0</td>\n",
- " <td>4</td>\n",
- " <td>139.990</td>\n",
- " <td>0.1450</td>\n",
- " <td>0.767</td>\n",
- " <td>0.576</td>\n",
- " <td>0.000003</td>\n",
- " <td>0.0968</td>\n",
- " <td>-9.683</td>\n",
- " <td>0.2560</td>\n",
- " <td>0.1870</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4SKqOHKYU5pgHr5UiVKiQN</th>\n",
- " <td>NaN</td>\n",
- " <td>Backpack</td>\n",
- " <td>Dark Trap</td>\n",
- " <td>135079</td>\n",
- " <td>5</td>\n",
- " <td>1</td>\n",
- " <td>4</td>\n",
- " <td>128.014</td>\n",
- " <td>0.0077</td>\n",
- " <td>0.765</td>\n",
- " <td>0.726</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.6190</td>\n",
- " <td>-5.580</td>\n",
- " <td>0.1910</td>\n",
- " <td>0.2700</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " title song_name genre duration_ms key mode \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p NaN Pathology Dark Trap 224427 8 1 \n",
- "0vSWgAlfpye0WCGeNmuNhy NaN Symbiote Dark Trap 98821 5 1 \n",
- "7EL7ifncK2PWFYThJjzR25 NaN BRAINFOOD Dark Trap 101172 8 1 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 NaN Sacrifice Dark Trap 96062 10 0 \n",
- "4SKqOHKYU5pgHr5UiVKiQN NaN Backpack Dark Trap 135079 5 1 \n",
- "\n",
- " time_signature tempo acousticness danceability \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 4 115.080 0.4010 0.719 \n",
- "0vSWgAlfpye0WCGeNmuNhy 4 218.050 0.0138 0.850 \n",
- "7EL7ifncK2PWFYThJjzR25 4 189.938 0.1870 0.864 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 4 139.990 0.1450 0.767 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 4 128.014 0.0077 0.765 \n",
- "\n",
- " energy instrumentalness liveness loudness \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.493 0.000000 0.1180 -7.230 \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.893 0.000004 0.3720 -4.783 \n",
- "7EL7ifncK2PWFYThJjzR25 0.365 0.000000 0.1160 -10.219 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.576 0.000003 0.0968 -9.683 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.726 0.000000 0.6190 -5.580 \n",
- "\n",
- " speechiness valence \n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.0794 0.1240 \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.0623 0.0391 \n",
- "7EL7ifncK2PWFYThJjzR25 0.0655 0.0478 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.2560 0.1870 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.1910 0.2700 "
- ]
- },
- "execution_count": 18,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "df.head()"
- ]
- },
{
"cell_type": "markdown",
"metadata": {
@@ -2347,7 +2141,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
@@ -2360,7 +2154,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -2381,7 +2175,7 @@
"Name: mode, Length: 35877, dtype: object"
]
},
- "execution_count": 20,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -2401,7 +2195,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 19,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -2428,13 +2222,13 @@
"Name: mode, Length: 35877, dtype: object"
]
},
- "execution_count": 21,
+ "execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df[\"mode\"].apply(lambda x: \"major\" if x == 1 else \"minor\")"
+ "df[\"mode\"].apply( lambda m: \"major\" if m == 1 else \"minor\" )"
]
},
{
@@ -2447,7 +2241,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 20,
"metadata": {},
"outputs": [
{
@@ -2634,7 +2428,7 @@
" <tr>\n",
" <th>46bXU7Sgj7104ZoXxzz9tM</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>269208</td>\n",
" <td>4</td>\n",
@@ -2654,7 +2448,7 @@
" <tr>\n",
" <th>0he2ViGMUO3ajKTxLOfWVT</th>\n",
" <td>Greatest Hardstyle Playlist</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>210112</td>\n",
" <td>0</td>\n",
@@ -2674,7 +2468,7 @@
" <tr>\n",
" <th>72DAt9Lbpy9EUS29OzQLob</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>234823</td>\n",
" <td>8</td>\n",
@@ -2694,7 +2488,7 @@
" <tr>\n",
" <th>6HXgExFVuE1c3cq9QjFCcU</th>\n",
" <td>Euphoric Hardstyle</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>323200</td>\n",
" <td>6</td>\n",
@@ -2714,7 +2508,7 @@
" <tr>\n",
" <th>6MAAMZImxcvYhRnxDLTufD</th>\n",
" <td>Best of Hardstyle 2020</td>\n",
- " <td>This song does not have a name</td>\n",
+ " <td>This song doesn't have a name</td>\n",
" <td>hardstyle</td>\n",
" <td>162161</td>\n",
" <td>9</td>\n",
@@ -2751,66 +2545,66 @@
"6HXgExFVuE1c3cq9QjFCcU Euphoric Hardstyle \n",
"6MAAMZImxcvYhRnxDLTufD Best of Hardstyle 2020 \n",
"\n",
- " song_name genre \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p Pathology Dark Trap \n",
- "0vSWgAlfpye0WCGeNmuNhy Symbiote Dark Trap \n",
- "7EL7ifncK2PWFYThJjzR25 BRAINFOOD Dark Trap \n",
- "1umsRbM7L4ju7rn9aU8Ju6 Sacrifice Dark Trap \n",
- "4SKqOHKYU5pgHr5UiVKiQN Backpack Dark Trap \n",
- "... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM This song does not have a name hardstyle \n",
- "0he2ViGMUO3ajKTxLOfWVT This song does not have a name hardstyle \n",
- "72DAt9Lbpy9EUS29OzQLob This song does not have a name hardstyle \n",
- "6HXgExFVuE1c3cq9QjFCcU This song does not have a name hardstyle \n",
- "6MAAMZImxcvYhRnxDLTufD This song does not have a name hardstyle \n",
+ " song_name genre duration_ms \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p Pathology Dark Trap 224427 \n",
+ "0vSWgAlfpye0WCGeNmuNhy Symbiote Dark Trap 98821 \n",
+ "7EL7ifncK2PWFYThJjzR25 BRAINFOOD Dark Trap 101172 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 Sacrifice Dark Trap 96062 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN Backpack Dark Trap 135079 \n",
+ "... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM This song doesn't have a name hardstyle 269208 \n",
+ "0he2ViGMUO3ajKTxLOfWVT This song doesn't have a name hardstyle 210112 \n",
+ "72DAt9Lbpy9EUS29OzQLob This song doesn't have a name hardstyle 234823 \n",
+ "6HXgExFVuE1c3cq9QjFCcU This song doesn't have a name hardstyle 323200 \n",
+ "6MAAMZImxcvYhRnxDLTufD This song doesn't have a name hardstyle 162161 \n",
"\n",
- " duration_ms key mode time_signature tempo \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 224427 8 1 4 115.080 \n",
- "0vSWgAlfpye0WCGeNmuNhy 98821 5 1 4 218.050 \n",
- "7EL7ifncK2PWFYThJjzR25 101172 8 1 4 189.938 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 96062 10 0 4 139.990 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 135079 5 1 4 128.014 \n",
- "... ... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 269208 4 1 4 150.013 \n",
- "0he2ViGMUO3ajKTxLOfWVT 210112 0 0 4 149.928 \n",
- "72DAt9Lbpy9EUS29OzQLob 234823 8 1 4 154.935 \n",
- "6HXgExFVuE1c3cq9QjFCcU 323200 6 0 4 150.042 \n",
- "6MAAMZImxcvYhRnxDLTufD 162161 9 1 4 155.047 \n",
+ " key mode time_signature tempo acousticness \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p 8 1 4 115.080 0.401000 \n",
+ "0vSWgAlfpye0WCGeNmuNhy 5 1 4 218.050 0.013800 \n",
+ "7EL7ifncK2PWFYThJjzR25 8 1 4 189.938 0.187000 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 10 0 4 139.990 0.145000 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN 5 1 4 128.014 0.007700 \n",
+ "... ... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 4 1 4 150.013 0.031500 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0 0 4 149.928 0.022500 \n",
+ "72DAt9Lbpy9EUS29OzQLob 8 1 4 154.935 0.026000 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 6 0 4 150.042 0.000551 \n",
+ "6MAAMZImxcvYhRnxDLTufD 9 1 4 155.047 0.001890 \n",
"\n",
- " acousticness danceability energy instrumentalness \\\n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.401000 0.719 0.493 0.000000 \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.013800 0.850 0.893 0.000004 \n",
- "7EL7ifncK2PWFYThJjzR25 0.187000 0.864 0.365 0.000000 \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.145000 0.767 0.576 0.000003 \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.007700 0.765 0.726 0.000000 \n",
- "... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.031500 0.528 0.693 0.000345 \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.022500 0.517 0.768 0.000018 \n",
- "72DAt9Lbpy9EUS29OzQLob 0.026000 0.361 0.821 0.000242 \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.000551 0.477 0.921 0.029600 \n",
- "6MAAMZImxcvYhRnxDLTufD 0.001890 0.529 0.945 0.000055 \n",
+ " danceability energy instrumentalness liveness \\\n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p 0.719 0.493 0.000000 0.1180 \n",
+ "0vSWgAlfpye0WCGeNmuNhy 0.850 0.893 0.000004 0.3720 \n",
+ "7EL7ifncK2PWFYThJjzR25 0.864 0.365 0.000000 0.1160 \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 0.767 0.576 0.000003 0.0968 \n",
+ "4SKqOHKYU5pgHr5UiVKiQN 0.765 0.726 0.000000 0.6190 \n",
+ "... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM 0.528 0.693 0.000345 0.1210 \n",
+ "0he2ViGMUO3ajKTxLOfWVT 0.517 0.768 0.000018 0.2050 \n",
+ "72DAt9Lbpy9EUS29OzQLob 0.361 0.821 0.000242 0.3850 \n",
+ "6HXgExFVuE1c3cq9QjFCcU 0.477 0.921 0.029600 0.0575 \n",
+ "6MAAMZImxcvYhRnxDLTufD 0.529 0.945 0.000055 0.4140 \n",
"\n",
- " liveness loudness speechiness valence modified_mode \n",
- "id \n",
- "7pgJBLVz5VmnL7uGHmRj6p 0.1180 -7.230 0.0794 0.1240 major \n",
- "0vSWgAlfpye0WCGeNmuNhy 0.3720 -4.783 0.0623 0.0391 major \n",
- "7EL7ifncK2PWFYThJjzR25 0.1160 -10.219 0.0655 0.0478 major \n",
- "1umsRbM7L4ju7rn9aU8Ju6 0.0968 -9.683 0.2560 0.1870 minor \n",
- "4SKqOHKYU5pgHr5UiVKiQN 0.6190 -5.580 0.1910 0.2700 major \n",
- "... ... ... ... ... ... \n",
- "46bXU7Sgj7104ZoXxzz9tM 0.1210 -5.148 0.0304 0.3940 major \n",
- "0he2ViGMUO3ajKTxLOfWVT 0.2050 -7.922 0.0479 0.3830 minor \n",
- "72DAt9Lbpy9EUS29OzQLob 0.3850 -3.102 0.0505 0.1240 major \n",
- "6HXgExFVuE1c3cq9QjFCcU 0.0575 -4.777 0.0392 0.4880 minor \n",
- "6MAAMZImxcvYhRnxDLTufD 0.4140 -5.862 0.0615 0.1340 major \n",
+ " loudness speechiness valence modified_mode \n",
+ "id \n",
+ "7pgJBLVz5VmnL7uGHmRj6p -7.230 0.0794 0.1240 major \n",
+ "0vSWgAlfpye0WCGeNmuNhy -4.783 0.0623 0.0391 major \n",
+ "7EL7ifncK2PWFYThJjzR25 -10.219 0.0655 0.0478 major \n",
+ "1umsRbM7L4ju7rn9aU8Ju6 -9.683 0.2560 0.1870 minor \n",
+ "4SKqOHKYU5pgHr5UiVKiQN -5.580 0.1910 0.2700 major \n",
+ "... ... ... ... ... \n",
+ "46bXU7Sgj7104ZoXxzz9tM -5.148 0.0304 0.3940 major \n",
+ "0he2ViGMUO3ajKTxLOfWVT -7.922 0.0479 0.3830 minor \n",
+ "72DAt9Lbpy9EUS29OzQLob -3.102 0.0505 0.1240 major \n",
+ "6HXgExFVuE1c3cq9QjFCcU -4.777 0.0392 0.4880 minor \n",
+ "6MAAMZImxcvYhRnxDLTufD -5.862 0.0615 0.1340 major \n",
"\n",
"[35877 rows x 17 columns]"
]
},
- "execution_count": 22,
+ "execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
@@ -2829,7 +2623,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": 21,
"metadata": {
"id": "ZoiyUleiyhMg"
},
@@ -3156,7 +2950,7 @@
"[35877 rows x 17 columns]"
]
},
- "execution_count": 23,
+ "execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
@@ -3175,7 +2969,7 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -3281,7 +3075,7 @@
"[35877 rows x 2 columns]"
]
},
- "execution_count": 24,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -3303,7 +3097,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 24,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -3312,6 +3106,41 @@
"id": "trRMgGMysdkb",
"outputId": "d02098c3-7722-4505-c599-5897bb8ace19"
},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<pandas.core.groupby.generic.DataFrameGroupBy object at 0x137459e40>"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[[\"genre\", \"duration_ms\"]].groupby(\"genre\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What is the average duration for each genre ordered based on decreasing order of averages?\n",
+ "#### v1: using `df` (`pandas`) to answer the question"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
"outputs": [
{
"data": {
@@ -3426,26 +3255,20 @@
"trap 225149.277731"
]
},
- "execution_count": 27,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
+ "# mean is our aggregation function\n",
+ "# it's not sorted yet\n",
"df[[\"genre\", \"duration_ms\"]].groupby(\"genre\").mean()"
]
},
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is the average duration for each genre ordered based on decreasing order of averages?\n",
- "#### v1: using `df` (`pandas`) to answer the question"
- ]
- },
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 28,
"metadata": {},
"outputs": [
{
@@ -3561,23 +3384,143 @@
"Trap Metal 145940.519467"
]
},
- "execution_count": 29,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "df[[\"genre\", \"duration_ms\"]].groupby('genre').mean() \\\n",
- " .sort_values(by=\"duration_ms\", ascending=False)"
+ "# let's sort it\n",
+ "df[[\"genre\", \"duration_ms\"]].groupby(\"genre\").mean()\\\n",
+ " .sort_values(by=\"duration_ms\" ,ascending=False)"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 26,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>duration_ms</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>genre</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Dark Trap</th>\n",
+ " <td>3590</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Emo</th>\n",
+ " <td>1622</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Hiphop</th>\n",
+ " <td>3027</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Pop</th>\n",
+ " <td>453</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rap</th>\n",
+ " <td>1546</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>RnB</th>\n",
+ " <td>1905</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Trap Metal</th>\n",
+ " <td>1875</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Underground Rap</th>\n",
+ " <td>4330</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>dnb</th>\n",
+ " <td>2507</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>hardstyle</th>\n",
+ " <td>2351</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>psytrance</th>\n",
+ " <td>2650</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>techhouse</th>\n",
+ " <td>2209</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>techno</th>\n",
+ " <td>2646</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>trance</th>\n",
+ " <td>2804</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>trap</th>\n",
+ " <td>2362</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " duration_ms\n",
+ "genre \n",
+ "Dark Trap 3590\n",
+ "Emo 1622\n",
+ "Hiphop 3027\n",
+ "Pop 453\n",
+ "Rap 1546\n",
+ "RnB 1905\n",
+ "Trap Metal 1875\n",
+ "Underground Rap 4330\n",
+ "dnb 2507\n",
+ "hardstyle 2351\n",
+ "psytrance 2650\n",
+ "techhouse 2209\n",
+ "techno 2646\n",
+ "trance 2804\n",
+ "trap 2362"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "df[[\"genre\", \"duration_ms\"]]"
+ "# another aggregation method is .count()\n",
+ "df[[\"genre\", \"duration_ms\"]].groupby(\"genre\").count()"
]
},
{
@@ -3589,7 +3532,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -3613,7 +3556,7 @@
"Name: genre, dtype: int64"
]
},
- "execution_count": 30,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -3632,7 +3575,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 33,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -3755,7 +3698,7 @@
"Trap Metal 145940.519467"
]
},
- "execution_count": 32,
+ "execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
@@ -3763,7 +3706,7 @@
"source": [
"# SQL equivalent query of the above Pandas query\n",
"avg_duration_per_genre = qry(\"\"\"\n",
- " SELECT genre, AVG(duration_ms) duration_avg\n",
+ " SELECT genre, AVG(duration_ms) AS duration_avg\n",
" FROM spotify\n",
" GROUP BY genre\n",
" ORDER BY duration_avg DESC\n",
@@ -3786,7 +3729,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 34,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -3878,7 +3821,7 @@
" 5 0.220177"
]
},
- "execution_count": 33,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -3886,13 +3829,13 @@
"source": [
"# use a list to indicate all the columns you want to groupby \n",
"groupby_cols = ['mode', 'time_signature']\n",
- "cols_to_keep = [\"mode\", \"time_signature\", \"speechiness\"]\n",
- "df[cols_to_keep].groupby(groupby_cols).mean()"
+ "df_cols = ['mode', 'time_signature', 'speechiness']\n",
+ "df[df_cols].groupby(groupby_cols).mean()\n"
]
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 35,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -3993,7 +3936,7 @@
"7 1 5 0.220177"
]
},
- "execution_count": 34,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -4001,15 +3944,15 @@
"source": [
"# SQL equivalent query of the above Pandas query\n",
"qry(\"\"\"\n",
- " SELECT mode, time_signature, AVG(speechiness) as avg_speechiness\n",
+ " SELECT mode, time_signature, AVG(speechiness) AS avg_speechiness\n",
" FROM spotify\n",
" GROUP BY mode, time_signature\n",
- "\"\"\")\n"
+ " \"\"\")"
]
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 36,
"metadata": {},
"outputs": [],
"source": [