Skip to content

F
FML_Project
You need to sign in or sign up before continuing.
Commit 8fb6df20 authored by Nilesh Jagdish's avatar Nilesh Jagdish
Browse files
Options

Updated RFRegressor

parent 06da3b97
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 360 deletions
RFRegressor/rf_new_data_80est.ipynb
View file @ 8fb6df20
......@@ -533,7 +533,7 @@
"outputs": [],
"source": [
"df = df[(df.trip_duration < 5900)]\n",
"# df = df[(df.trip_duration > 60)]"
"df = df[(df.trip_duration > 60)]"
]
},
{
......@@ -556,212 +556,6 @@
"df = df[(df.passenger_count > 0)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 320
},
"id": "TvMqWf8jT1ab",
"outputId": "7b434c36-cbbc-4245-86ce-8be38db62dfb"
},
"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>vendor_id</th>\n",
" <th>passenger_count</th>\n",
" <th>pickup_longitude</th>\n",
" <th>pickup_latitude</th>\n",
" <th>dropoff_longitude</th>\n",
" <th>dropoff_latitude</th>\n",
" <th>trip_duration</th>\n",
" <th>vism</th>\n",
" <th>fog</th>\n",
" <th>rain</th>\n",
" <th>snow</th>\n",
" <th>holiday_or_not</th>\n",
" <th>turns</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" <td>1.456018e+06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>1.534277e+00</td>\n",
" <td>1.664016e+00</td>\n",
" <td>-7.397352e+01</td>\n",
" <td>4.075094e+01</td>\n",
" <td>-7.397343e+01</td>\n",
" <td>4.075181e+01</td>\n",
" <td>8.348868e+02</td>\n",
" <td>1.467787e+01</td>\n",
" <td>6.518463e-03</td>\n",
" <td>9.605307e-02</td>\n",
" <td>2.387539e-02</td>\n",
" <td>1.868590e-02</td>\n",
" <td>7.543262e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>4.988239e-01</td>\n",
" <td>1.313631e+00</td>\n",
" <td>7.088238e-02</td>\n",
" <td>3.284235e-02</td>\n",
" <td>7.061578e-02</td>\n",
" <td>3.585719e-02</td>\n",
" <td>6.491411e+02</td>\n",
" <td>3.070585e+00</td>\n",
" <td>1.124494e-01</td>\n",
" <td>5.186673e-01</td>\n",
" <td>2.773547e-01</td>\n",
" <td>1.354132e-01</td>\n",
" <td>4.428224e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-1.219333e+02</td>\n",
" <td>3.435970e+01</td>\n",
" <td>-1.219333e+02</td>\n",
" <td>3.218114e+01</td>\n",
" <td>1.000000e+00</td>\n",
" <td>4.000000e-01</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>2.000000e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>1.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-7.399187e+01</td>\n",
" <td>4.073737e+01</td>\n",
" <td>-7.399133e+01</td>\n",
" <td>4.073590e+01</td>\n",
" <td>3.970000e+02</td>\n",
" <td>1.450000e+01</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>5.000000e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>2.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-7.398174e+01</td>\n",
" <td>4.075411e+01</td>\n",
" <td>-7.397975e+01</td>\n",
" <td>4.075453e+01</td>\n",
" <td>6.610000e+02</td>\n",
" <td>1.610000e+01</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>6.000000e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>2.000000e+00</td>\n",
" <td>2.000000e+00</td>\n",
" <td>-7.396735e+01</td>\n",
" <td>4.076836e+01</td>\n",
" <td>-7.396302e+01</td>\n",
" <td>4.076982e+01</td>\n",
" <td>1.072000e+03</td>\n",
" <td>1.610000e+01</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>0.000000e+00</td>\n",
" <td>9.000000e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>2.000000e+00</td>\n",
" <td>9.000000e+00</td>\n",
" <td>-6.133553e+01</td>\n",
" <td>5.188108e+01</td>\n",
" <td>-6.133553e+01</td>\n",
" <td>4.392103e+01</td>\n",
" <td>5.999000e+03</td>\n",
" <td>1.610000e+01</td>\n",
" <td>4.000000e+00</td>\n",
" <td>7.000000e+00</td>\n",
" <td>6.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>4.600000e+01</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" vendor_id passenger_count ... holiday_or_not turns\n",
"count 1.456018e+06 1.456018e+06 ... 1.456018e+06 1.456018e+06\n",
"mean 1.534277e+00 1.664016e+00 ... 1.868590e-02 7.543262e+00\n",
"std 4.988239e-01 1.313631e+00 ... 1.354132e-01 4.428224e+00\n",
"min 1.000000e+00 1.000000e+00 ... 0.000000e+00 2.000000e+00\n",
"25% 1.000000e+00 1.000000e+00 ... 0.000000e+00 5.000000e+00\n",
"50% 2.000000e+00 1.000000e+00 ... 0.000000e+00 6.000000e+00\n",
"75% 2.000000e+00 2.000000e+00 ... 0.000000e+00 9.000000e+00\n",
"max 2.000000e+00 9.000000e+00 ... 1.000000e+00 4.600000e+01\n",
"\n",
"[8 rows x 13 columns]"
]
},
"execution_count": 22,
"metadata": {
"tags": []
},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {
......
RFRegressor/rf_old_data_50est.ipynb
View file @ 8fb6df20
......@@ -306,7 +306,7 @@
"outputs": [],
"source": [
"df = df[(df.trip_duration < 5900)]\n",
"# df = df[(df.trip_duration > 60)]"
"df = df[(df.trip_duration > 60)]"
]
},
{
......@@ -329,158 +329,6 @@
"df = df[(df.passenger_count > 0)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 320
},
"id": "TvMqWf8jT1ab",
"outputId": "c9e22ea9-3cb5-4c14-b4c2-bb7b31de5062"
},
"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>vendor_id</th>\n",
" <th>passenger_count</th>\n",
" <th>pickup_longitude</th>\n",
" <th>pickup_latitude</th>\n",
" <th>dropoff_longitude</th>\n",
" <th>dropoff_latitude</th>\n",
" <th>trip_duration</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" <td>1.455957e+06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>1.534271e+00</td>\n",
" <td>1.664020e+00</td>\n",
" <td>-7.397352e+01</td>\n",
" <td>4.075095e+01</td>\n",
" <td>-7.397343e+01</td>\n",
" <td>4.075181e+01</td>\n",
" <td>8.346726e+02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>4.988243e-01</td>\n",
" <td>1.313639e+00</td>\n",
" <td>7.087820e-02</td>\n",
" <td>3.283941e-02</td>\n",
" <td>7.060772e-02</td>\n",
" <td>3.584790e-02</td>\n",
" <td>6.483105e+02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-1.219333e+02</td>\n",
" <td>3.435970e+01</td>\n",
" <td>-1.219333e+02</td>\n",
" <td>3.218114e+01</td>\n",
" <td>1.000000e+00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>1.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-7.399187e+01</td>\n",
" <td>4.073737e+01</td>\n",
" <td>-7.399133e+01</td>\n",
" <td>4.073590e+01</td>\n",
" <td>3.970000e+02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>2.000000e+00</td>\n",
" <td>1.000000e+00</td>\n",
" <td>-7.398174e+01</td>\n",
" <td>4.075411e+01</td>\n",
" <td>-7.397975e+01</td>\n",
" <td>4.075453e+01</td>\n",
" <td>6.610000e+02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>2.000000e+00</td>\n",
" <td>2.000000e+00</td>\n",
" <td>-7.396735e+01</td>\n",
" <td>4.076836e+01</td>\n",
" <td>-7.396302e+01</td>\n",
" <td>4.076982e+01</td>\n",
" <td>1.072000e+03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>2.000000e+00</td>\n",
" <td>9.000000e+00</td>\n",
" <td>-6.133553e+01</td>\n",
" <td>5.188108e+01</td>\n",
" <td>-6.133553e+01</td>\n",
" <td>4.392103e+01</td>\n",
" <td>5.897000e+03</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" vendor_id passenger_count ... dropoff_latitude trip_duration\n",
"count 1.455957e+06 1.455957e+06 ... 1.455957e+06 1.455957e+06\n",
"mean 1.534271e+00 1.664020e+00 ... 4.075181e+01 8.346726e+02\n",
"std 4.988243e-01 1.313639e+00 ... 3.584790e-02 6.483105e+02\n",
"min 1.000000e+00 1.000000e+00 ... 3.218114e+01 1.000000e+00\n",
"25% 1.000000e+00 1.000000e+00 ... 4.073590e+01 3.970000e+02\n",
"50% 2.000000e+00 1.000000e+00 ... 4.075453e+01 6.610000e+02\n",
"75% 2.000000e+00 2.000000e+00 ... 4.076982e+01 1.072000e+03\n",
"max 2.000000e+00 9.000000e+00 ... 4.392103e+01 5.897000e+03\n",
"\n",
"[8 rows x 7 columns]"
]
},
"execution_count": 8,
"metadata": {
"tags": []
},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment