├── Session1
    ├── concat year month day and product permutation.ipynb
    ├── df.clipboard_convert table to df.ipynb
    ├── dropna threshold percentage row and column.ipynb
    ├── filter by groupby.ipynb
    ├── get rid of Unnamed in df.ipynb
    ├── groupby agg multindex drop level.ipynb
    ├── insert and change column order in pandas.ipynb
    └── regex eliminate string and convert string to float.ipynb
├── Session2
    ├── If_Reads_Numerical_Values_As_Object_-_pandas.read_csv.ipynb
    ├── Quick_One-Hot_Encoding_with_Pandas.ipynb
    ├── Quick_Web_Scraping_with_Pandas.ipynb
    ├── create others values in pandas column.ipynb
    ├── map function and assign numbers to category (factorize) and boolean.ipynb
    └── select columns by slicing pandas.ipynb
├── Session3
    ├── Deal_with_zip_files.ipynb
    ├── Parquet_and_Pickle_instead_of_CSV.ipynb
    ├── count words in row.ipynb
    ├── pd.cut pd.qcut.ipynb
    ├── query_Dataframe.ipynb
    └── transform sum pandas column.ipynb
├── Session4
    ├── load autotime for every cell runtime and select_dtypes.ipynb
    └── swifter apply fastest run.ipynb
└── Session5
    ├── pd.to_numeric errors coerce.ipynb
    └── random create dataframe.ipynb


/Session1/concat year month day and product permutation.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "3d1a84ee",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>year</th>\n",
 31 |        "      <th>month</th>\n",
 32 |        "      <th>day</th>\n",
 33 |        "      <th>data</th>\n",
 34 |        "    </tr>\n",
 35 |        "  </thead>\n",
 36 |        "  <tbody>\n",
 37 |        "    <tr>\n",
 38 |        "      <th>2017-01-01</th>\n",
 39 |        "      <td>2017</td>\n",
 40 |        "      <td>1</td>\n",
 41 |        "      <td>1</td>\n",
 42 |        "      <td>-0.773084</td>\n",
 43 |        "    </tr>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>2017-01-02</th>\n",
 46 |        "      <td>2017</td>\n",
 47 |        "      <td>1</td>\n",
 48 |        "      <td>2</td>\n",
 49 |        "      <td>-0.239255</td>\n",
 50 |        "    </tr>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>2017-01-03</th>\n",
 53 |        "      <td>2017</td>\n",
 54 |        "      <td>1</td>\n",
 55 |        "      <td>3</td>\n",
 56 |        "      <td>0.557760</td>\n",
 57 |        "    </tr>\n",
 58 |        "    <tr>\n",
 59 |        "      <th>2017-02-01</th>\n",
 60 |        "      <td>2017</td>\n",
 61 |        "      <td>2</td>\n",
 62 |        "      <td>1</td>\n",
 63 |        "      <td>-0.952520</td>\n",
 64 |        "    </tr>\n",
 65 |        "    <tr>\n",
 66 |        "      <th>2017-02-02</th>\n",
 67 |        "      <td>2017</td>\n",
 68 |        "      <td>2</td>\n",
 69 |        "      <td>2</td>\n",
 70 |        "      <td>0.269137</td>\n",
 71 |        "    </tr>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>2017-02-03</th>\n",
 74 |        "      <td>2017</td>\n",
 75 |        "      <td>2</td>\n",
 76 |        "      <td>3</td>\n",
 77 |        "      <td>-0.581972</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>2016-01-01</th>\n",
 81 |        "      <td>2016</td>\n",
 82 |        "      <td>1</td>\n",
 83 |        "      <td>1</td>\n",
 84 |        "      <td>-0.724717</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>2016-01-02</th>\n",
 88 |        "      <td>2016</td>\n",
 89 |        "      <td>1</td>\n",
 90 |        "      <td>2</td>\n",
 91 |        "      <td>0.886955</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>2016-01-03</th>\n",
 95 |        "      <td>2016</td>\n",
 96 |        "      <td>1</td>\n",
 97 |        "      <td>3</td>\n",
 98 |        "      <td>-1.272199</td>\n",
 99 |        "    </tr>\n",
100 |        "    <tr>\n",
101 |        "      <th>2016-02-01</th>\n",
102 |        "      <td>2016</td>\n",
103 |        "      <td>2</td>\n",
104 |        "      <td>1</td>\n",
105 |        "      <td>-0.165526</td>\n",
106 |        "    </tr>\n",
107 |        "    <tr>\n",
108 |        "      <th>2016-02-02</th>\n",
109 |        "      <td>2016</td>\n",
110 |        "      <td>2</td>\n",
111 |        "      <td>2</td>\n",
112 |        "      <td>2.148330</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>2016-02-03</th>\n",
116 |        "      <td>2016</td>\n",
117 |        "      <td>2</td>\n",
118 |        "      <td>3</td>\n",
119 |        "      <td>-0.091643</td>\n",
120 |        "    </tr>\n",
121 |        "  </tbody>\n",
122 |        "</table>\n",
123 |        "</div>"
124 |       ],
125 |       "text/plain": [
126 |        "            year  month  day      data\n",
127 |        "2017-01-01  2017      1    1 -0.773084\n",
128 |        "2017-01-02  2017      1    2 -0.239255\n",
129 |        "2017-01-03  2017      1    3  0.557760\n",
130 |        "2017-02-01  2017      2    1 -0.952520\n",
131 |        "2017-02-02  2017      2    2  0.269137\n",
132 |        "2017-02-03  2017      2    3 -0.581972\n",
133 |        "2016-01-01  2016      1    1 -0.724717\n",
134 |        "2016-01-02  2016      1    2  0.886955\n",
135 |        "2016-01-03  2016      1    3 -1.272199\n",
136 |        "2016-02-01  2016      2    1 -0.165526\n",
137 |        "2016-02-02  2016      2    2  2.148330\n",
138 |        "2016-02-03  2016      2    3 -0.091643"
139 |       ]
140 |      },
141 |      "execution_count": 2,
142 |      "metadata": {},
143 |      "output_type": "execute_result"
144 |     }
145 |    ],
146 |    "source": [
147 |     "import numpy as np\n",
148 |     "import pandas as pd\n",
149 |     "\n",
150 |     "from itertools import product\n",
151 |     "\n",
152 |     "datecols = ['year', 'month', 'day']\n",
153 |     "\n",
154 |     "df = pd.DataFrame(list(product([2017, 2016], [1, 2], [1, 2, 3])),\n",
155 |     "                  columns=datecols)\n",
156 |     "\n",
157 |     "df['data'] = np.random.randn(len(df))\n",
158 |     "\n",
159 |     "df.index = pd.to_datetime(df[datecols])\n",
160 |     "df"
161 |    ]
162 |   },
163 |   {
164 |    "cell_type": "code",
165 |    "execution_count": null,
166 |    "id": "43f7309f",
167 |    "metadata": {},
168 |    "outputs": [],
169 |    "source": []
170 |   }
171 |  ],
172 |  "metadata": {
173 |   "kernelspec": {
174 |    "display_name": "Python 3 (ipykernel)",
175 |    "language": "python",
176 |    "name": "python3"
177 |   },
178 |   "language_info": {
179 |    "codemirror_mode": {
180 |     "name": "ipython",
181 |     "version": 3
182 |    },
183 |    "file_extension": ".py",
184 |    "mimetype": "text/x-python",
185 |    "name": "python",
186 |    "nbconvert_exporter": "python",
187 |    "pygments_lexer": "ipython3",
188 |    "version": "3.9.13"
189 |   }
190 |  },
191 |  "nbformat": 4,
192 |  "nbformat_minor": 5
193 | }
194 | 


--------------------------------------------------------------------------------
/Session1/df.clipboard_convert table to df.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "id": "06e38720",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "year\tmonth\tday\tdata\n",
 11 |     "2017-01-01\t2017\t1\t1\t-1.343786\n",
 12 |     "2017-01-02\t2017\t1\t2\t-0.314145\n",
 13 |     "2017-01-03\t2017\t1\t3\t0.639521\n",
 14 |     "2017-02-01\t2017\t2\t1\t0.355203\n",
 15 |     "2017-02-02\t2017\t2\t2\t-0.959005"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "code",
 20 |    "execution_count": 1,
 21 |    "id": "9e2ad1f1",
 22 |    "metadata": {},
 23 |    "outputs": [
 24 |     {
 25 |      "data": {
 26 |       "text/html": [
 27 |        "<div>\n",
 28 |        "<style scoped>\n",
 29 |        "    .dataframe tbody tr th:only-of-type {\n",
 30 |        "        vertical-align: middle;\n",
 31 |        "    }\n",
 32 |        "\n",
 33 |        "    .dataframe tbody tr th {\n",
 34 |        "        vertical-align: top;\n",
 35 |        "    }\n",
 36 |        "\n",
 37 |        "    .dataframe thead th {\n",
 38 |        "        text-align: right;\n",
 39 |        "    }\n",
 40 |        "</style>\n",
 41 |        "<table border=\"1\" class=\"dataframe\">\n",
 42 |        "  <thead>\n",
 43 |        "    <tr style=\"text-align: right;\">\n",
 44 |        "      <th></th>\n",
 45 |        "      <th>year</th>\n",
 46 |        "      <th>month</th>\n",
 47 |        "      <th>day</th>\n",
 48 |        "      <th>data</th>\n",
 49 |        "    </tr>\n",
 50 |        "  </thead>\n",
 51 |        "  <tbody>\n",
 52 |        "    <tr>\n",
 53 |        "      <th>2017-01-01</th>\n",
 54 |        "      <td>2017</td>\n",
 55 |        "      <td>1</td>\n",
 56 |        "      <td>1</td>\n",
 57 |        "      <td>-1.343786</td>\n",
 58 |        "    </tr>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>2017-01-02</th>\n",
 61 |        "      <td>2017</td>\n",
 62 |        "      <td>1</td>\n",
 63 |        "      <td>2</td>\n",
 64 |        "      <td>-0.314145</td>\n",
 65 |        "    </tr>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>2017-01-03</th>\n",
 68 |        "      <td>2017</td>\n",
 69 |        "      <td>1</td>\n",
 70 |        "      <td>3</td>\n",
 71 |        "      <td>0.639521</td>\n",
 72 |        "    </tr>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>2017-02-01</th>\n",
 75 |        "      <td>2017</td>\n",
 76 |        "      <td>2</td>\n",
 77 |        "      <td>1</td>\n",
 78 |        "      <td>0.355203</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>2017-02-02</th>\n",
 82 |        "      <td>2017</td>\n",
 83 |        "      <td>2</td>\n",
 84 |        "      <td>2</td>\n",
 85 |        "      <td>-0.959005</td>\n",
 86 |        "    </tr>\n",
 87 |        "  </tbody>\n",
 88 |        "</table>\n",
 89 |        "</div>"
 90 |       ],
 91 |       "text/plain": [
 92 |        "            year  month  day      data\n",
 93 |        "2017-01-01  2017      1    1 -1.343786\n",
 94 |        "2017-01-02  2017      1    2 -0.314145\n",
 95 |        "2017-01-03  2017      1    3  0.639521\n",
 96 |        "2017-02-01  2017      2    1  0.355203\n",
 97 |        "2017-02-02  2017      2    2 -0.959005"
 98 |       ]
 99 |      },
100 |      "execution_count": 1,
101 |      "metadata": {},
102 |      "output_type": "execute_result"
103 |     }
104 |    ],
105 |    "source": [
106 |     "import pandas as pd \n",
107 |     "df = pd.read_clipboard()\n",
108 |     "df"
109 |    ]
110 |   },
111 |   {
112 |    "cell_type": "code",
113 |    "execution_count": null,
114 |    "id": "cec8dab3",
115 |    "metadata": {},
116 |    "outputs": [],
117 |    "source": []
118 |   }
119 |  ],
120 |  "metadata": {
121 |   "kernelspec": {
122 |    "display_name": "Python 3 (ipykernel)",
123 |    "language": "python",
124 |    "name": "python3"
125 |   },
126 |   "language_info": {
127 |    "codemirror_mode": {
128 |     "name": "ipython",
129 |     "version": 3
130 |    },
131 |    "file_extension": ".py",
132 |    "mimetype": "text/x-python",
133 |    "name": "python",
134 |    "nbconvert_exporter": "python",
135 |    "pygments_lexer": "ipython3",
136 |    "version": "3.9.13"
137 |   }
138 |  },
139 |  "nbformat": 4,
140 |  "nbformat_minor": 5
141 | }
142 | 


--------------------------------------------------------------------------------
/Session1/dropna threshold percentage row and column.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 10,
  6 |    "id": "36609d75",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>A</th>\n",
 31 |        "      <th>B</th>\n",
 32 |        "      <th>C</th>\n",
 33 |        "    </tr>\n",
 34 |        "  </thead>\n",
 35 |        "  <tbody>\n",
 36 |        "    <tr>\n",
 37 |        "      <th>0</th>\n",
 38 |        "      <td>2.0</td>\n",
 39 |        "      <td>2.0</td>\n",
 40 |        "      <td>3.0</td>\n",
 41 |        "    </tr>\n",
 42 |        "    <tr>\n",
 43 |        "      <th>1</th>\n",
 44 |        "      <td>6.0</td>\n",
 45 |        "      <td>2.0</td>\n",
 46 |        "      <td>NaN</td>\n",
 47 |        "    </tr>\n",
 48 |        "    <tr>\n",
 49 |        "      <th>2</th>\n",
 50 |        "      <td>NaN</td>\n",
 51 |        "      <td>NaN</td>\n",
 52 |        "      <td>NaN</td>\n",
 53 |        "    </tr>\n",
 54 |        "    <tr>\n",
 55 |        "      <th>3</th>\n",
 56 |        "      <td>9.0</td>\n",
 57 |        "      <td>5.0</td>\n",
 58 |        "      <td>NaN</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>4</th>\n",
 62 |        "      <td>9.0</td>\n",
 63 |        "      <td>8.0</td>\n",
 64 |        "      <td>NaN</td>\n",
 65 |        "    </tr>\n",
 66 |        "  </tbody>\n",
 67 |        "</table>\n",
 68 |        "</div>"
 69 |       ],
 70 |       "text/plain": [
 71 |        "     A    B    C\n",
 72 |        "0  2.0  2.0  3.0\n",
 73 |        "1  6.0  2.0  NaN\n",
 74 |        "2  NaN  NaN  NaN\n",
 75 |        "3  9.0  5.0  NaN\n",
 76 |        "4  9.0  8.0  NaN"
 77 |       ]
 78 |      },
 79 |      "execution_count": 10,
 80 |      "metadata": {},
 81 |      "output_type": "execute_result"
 82 |     }
 83 |    ],
 84 |    "source": [
 85 |     "import pandas as pd\n",
 86 |     "import numpy as np\n",
 87 |     "df = pd.DataFrame(dict(A=[2,6,np.nan,9,9],\n",
 88 |     "                       B=[2,2,np.nan,5,8], \n",
 89 |     "                       C=[3,np.nan,np.nan,np.nan,np.nan]))\n",
 90 |     "df"
 91 |    ]
 92 |   },
 93 |   {
 94 |    "cell_type": "code",
 95 |    "execution_count": 28,
 96 |    "id": "1955b2ae",
 97 |    "metadata": {},
 98 |    "outputs": [
 99 |     {
100 |      "data": {
101 |       "text/html": [
102 |        "<div>\n",
103 |        "<style scoped>\n",
104 |        "    .dataframe tbody tr th:only-of-type {\n",
105 |        "        vertical-align: middle;\n",
106 |        "    }\n",
107 |        "\n",
108 |        "    .dataframe tbody tr th {\n",
109 |        "        vertical-align: top;\n",
110 |        "    }\n",
111 |        "\n",
112 |        "    .dataframe thead th {\n",
113 |        "        text-align: right;\n",
114 |        "    }\n",
115 |        "</style>\n",
116 |        "<table border=\"1\" class=\"dataframe\">\n",
117 |        "  <thead>\n",
118 |        "    <tr style=\"text-align: right;\">\n",
119 |        "      <th></th>\n",
120 |        "    </tr>\n",
121 |        "  </thead>\n",
122 |        "  <tbody>\n",
123 |        "    <tr>\n",
124 |        "      <th>0</th>\n",
125 |        "    </tr>\n",
126 |        "    <tr>\n",
127 |        "      <th>1</th>\n",
128 |        "    </tr>\n",
129 |        "    <tr>\n",
130 |        "      <th>2</th>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>3</th>\n",
134 |        "    </tr>\n",
135 |        "    <tr>\n",
136 |        "      <th>4</th>\n",
137 |        "    </tr>\n",
138 |        "  </tbody>\n",
139 |        "</table>\n",
140 |        "</div>"
141 |       ],
142 |       "text/plain": [
143 |        "Empty DataFrame\n",
144 |        "Columns: []\n",
145 |        "Index: [0, 1, 2, 3, 4]"
146 |       ]
147 |      },
148 |      "execution_count": 28,
149 |      "metadata": {},
150 |      "output_type": "execute_result"
151 |     }
152 |    ],
153 |    "source": [
154 |     "df.dropna(thresh=5, axis='columns')"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": 8,
160 |    "id": "defe7bb4",
161 |    "metadata": {},
162 |    "outputs": [
163 |     {
164 |      "data": {
165 |       "text/plain": [
166 |        "3"
167 |       ]
168 |      },
169 |      "execution_count": 8,
170 |      "metadata": {},
171 |      "output_type": "execute_result"
172 |     }
173 |    ],
174 |    "source": [
175 |     "df.shape[1]"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "code",
180 |    "execution_count": 6,
181 |    "id": "bc65a8ed",
182 |    "metadata": {},
183 |    "outputs": [
184 |     {
185 |      "data": {
186 |       "text/html": [
187 |        "<div>\n",
188 |        "<style scoped>\n",
189 |        "    .dataframe tbody tr th:only-of-type {\n",
190 |        "        vertical-align: middle;\n",
191 |        "    }\n",
192 |        "\n",
193 |        "    .dataframe tbody tr th {\n",
194 |        "        vertical-align: top;\n",
195 |        "    }\n",
196 |        "\n",
197 |        "    .dataframe thead th {\n",
198 |        "        text-align: right;\n",
199 |        "    }\n",
200 |        "</style>\n",
201 |        "<table border=\"1\" class=\"dataframe\">\n",
202 |        "  <thead>\n",
203 |        "    <tr style=\"text-align: right;\">\n",
204 |        "      <th></th>\n",
205 |        "      <th>A</th>\n",
206 |        "      <th>B</th>\n",
207 |        "      <th>C</th>\n",
208 |        "    </tr>\n",
209 |        "  </thead>\n",
210 |        "  <tbody>\n",
211 |        "    <tr>\n",
212 |        "      <th>0</th>\n",
213 |        "      <td>2.0</td>\n",
214 |        "      <td>2.0</td>\n",
215 |        "      <td>3.0</td>\n",
216 |        "    </tr>\n",
217 |        "  </tbody>\n",
218 |        "</table>\n",
219 |        "</div>"
220 |       ],
221 |       "text/plain": [
222 |        "     A    B    C\n",
223 |        "0  2.0  2.0  3.0"
224 |       ]
225 |      },
226 |      "execution_count": 6,
227 |      "metadata": {},
228 |      "output_type": "execute_result"
229 |     }
230 |    ],
231 |    "source": [
232 |     "df.dropna(thresh=df.shape[1]*0.8, axis='rows')\n"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": 9,
238 |    "id": "d713a4f7",
239 |    "metadata": {},
240 |    "outputs": [
241 |     {
242 |      "data": {
243 |       "text/plain": [
244 |        "5"
245 |       ]
246 |      },
247 |      "execution_count": 9,
248 |      "metadata": {},
249 |      "output_type": "execute_result"
250 |     }
251 |    ],
252 |    "source": [
253 |     "df.shape[0]"
254 |    ]
255 |   },
256 |   {
257 |    "cell_type": "code",
258 |    "execution_count": 24,
259 |    "id": "6e9159be",
260 |    "metadata": {},
261 |    "outputs": [
262 |     {
263 |      "data": {
264 |       "text/html": [
265 |        "<div>\n",
266 |        "<style scoped>\n",
267 |        "    .dataframe tbody tr th:only-of-type {\n",
268 |        "        vertical-align: middle;\n",
269 |        "    }\n",
270 |        "\n",
271 |        "    .dataframe tbody tr th {\n",
272 |        "        vertical-align: top;\n",
273 |        "    }\n",
274 |        "\n",
275 |        "    .dataframe thead th {\n",
276 |        "        text-align: right;\n",
277 |        "    }\n",
278 |        "</style>\n",
279 |        "<table border=\"1\" class=\"dataframe\">\n",
280 |        "  <thead>\n",
281 |        "    <tr style=\"text-align: right;\">\n",
282 |        "      <th></th>\n",
283 |        "      <th>A</th>\n",
284 |        "      <th>B</th>\n",
285 |        "      <th>C</th>\n",
286 |        "    </tr>\n",
287 |        "  </thead>\n",
288 |        "  <tbody>\n",
289 |        "    <tr>\n",
290 |        "      <th>0</th>\n",
291 |        "      <td>2.0</td>\n",
292 |        "      <td>2.0</td>\n",
293 |        "      <td>3.0</td>\n",
294 |        "    </tr>\n",
295 |        "    <tr>\n",
296 |        "      <th>1</th>\n",
297 |        "      <td>6.0</td>\n",
298 |        "      <td>2.0</td>\n",
299 |        "      <td>NaN</td>\n",
300 |        "    </tr>\n",
301 |        "    <tr>\n",
302 |        "      <th>2</th>\n",
303 |        "      <td>NaN</td>\n",
304 |        "      <td>NaN</td>\n",
305 |        "      <td>NaN</td>\n",
306 |        "    </tr>\n",
307 |        "    <tr>\n",
308 |        "      <th>3</th>\n",
309 |        "      <td>9.0</td>\n",
310 |        "      <td>5.0</td>\n",
311 |        "      <td>NaN</td>\n",
312 |        "    </tr>\n",
313 |        "    <tr>\n",
314 |        "      <th>4</th>\n",
315 |        "      <td>9.0</td>\n",
316 |        "      <td>8.0</td>\n",
317 |        "      <td>NaN</td>\n",
318 |        "    </tr>\n",
319 |        "  </tbody>\n",
320 |        "</table>\n",
321 |        "</div>"
322 |       ],
323 |       "text/plain": [
324 |        "     A    B    C\n",
325 |        "0  2.0  2.0  3.0\n",
326 |        "1  6.0  2.0  NaN\n",
327 |        "2  NaN  NaN  NaN\n",
328 |        "3  9.0  5.0  NaN\n",
329 |        "4  9.0  8.0  NaN"
330 |       ]
331 |      },
332 |      "execution_count": 24,
333 |      "metadata": {},
334 |      "output_type": "execute_result"
335 |     }
336 |    ],
337 |    "source": [
338 |     "df.dropna(thresh=1, axis='columns')"
339 |    ]
340 |   },
341 |   {
342 |    "cell_type": "code",
343 |    "execution_count": null,
344 |    "id": "b249cdca",
345 |    "metadata": {},
346 |    "outputs": [],
347 |    "source": [
348 |     "import pandas as pd\n",
349 |     "df = pd.DataFrame(dict(A=[2,6,3],\n",
350 |     "                       B=[2,2,6], \n",
351 |     "                       C=[3,2,3]))\n",
352 |     "df.to_csv(\"datas.csv\",index=False)\n",
353 |     "\n",
354 |     "df = pd.read_csv(\"datas.csv\")\n",
355 |     "df"
356 |    ]
357 |   },
358 |   {
359 |    "cell_type": "code",
360 |    "execution_count": null,
361 |    "id": "2782b875",
362 |    "metadata": {},
363 |    "outputs": [],
364 |    "source": [
365 |     "df = pd.read_csv(\"datas.csv\", index_col=False)\n",
366 |     "df"
367 |    ]
368 |   }
369 |  ],
370 |  "metadata": {
371 |   "kernelspec": {
372 |    "display_name": "Python 3 (ipykernel)",
373 |    "language": "python",
374 |    "name": "python3"
375 |   },
376 |   "language_info": {
377 |    "codemirror_mode": {
378 |     "name": "ipython",
379 |     "version": 3
380 |    },
381 |    "file_extension": ".py",
382 |    "mimetype": "text/x-python",
383 |    "name": "python",
384 |    "nbconvert_exporter": "python",
385 |    "pygments_lexer": "ipython3",
386 |    "version": "3.9.13"
387 |   }
388 |  },
389 |  "nbformat": 4,
390 |  "nbformat_minor": 5
391 | }
392 | 


--------------------------------------------------------------------------------
/Session1/filter by groupby.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 6,
  6 |    "id": "f73bff90",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>A</th>\n",
 31 |        "      <th>B</th>\n",
 32 |        "      <th>C</th>\n",
 33 |        "    </tr>\n",
 34 |        "  </thead>\n",
 35 |        "  <tbody>\n",
 36 |        "    <tr>\n",
 37 |        "      <th>0</th>\n",
 38 |        "      <td>2.0</td>\n",
 39 |        "      <td>2.0</td>\n",
 40 |        "      <td>3.0</td>\n",
 41 |        "    </tr>\n",
 42 |        "    <tr>\n",
 43 |        "      <th>1</th>\n",
 44 |        "      <td>6.0</td>\n",
 45 |        "      <td>2.0</td>\n",
 46 |        "      <td>2.0</td>\n",
 47 |        "    </tr>\n",
 48 |        "    <tr>\n",
 49 |        "      <th>2</th>\n",
 50 |        "      <td>NaN</td>\n",
 51 |        "      <td>NaN</td>\n",
 52 |        "      <td>3.0</td>\n",
 53 |        "    </tr>\n",
 54 |        "    <tr>\n",
 55 |        "      <th>3</th>\n",
 56 |        "      <td>9.0</td>\n",
 57 |        "      <td>5.0</td>\n",
 58 |        "      <td>6.0</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>4</th>\n",
 62 |        "      <td>9.0</td>\n",
 63 |        "      <td>5.0</td>\n",
 64 |        "      <td>NaN</td>\n",
 65 |        "    </tr>\n",
 66 |        "  </tbody>\n",
 67 |        "</table>\n",
 68 |        "</div>"
 69 |       ],
 70 |       "text/plain": [
 71 |        "     A    B    C\n",
 72 |        "0  2.0  2.0  3.0\n",
 73 |        "1  6.0  2.0  2.0\n",
 74 |        "2  NaN  NaN  3.0\n",
 75 |        "3  9.0  5.0  6.0\n",
 76 |        "4  9.0  5.0  NaN"
 77 |       ]
 78 |      },
 79 |      "execution_count": 6,
 80 |      "metadata": {},
 81 |      "output_type": "execute_result"
 82 |     }
 83 |    ],
 84 |    "source": [
 85 |     "import pandas as pd\n",
 86 |     "import numpy as np\n",
 87 |     "df = pd.DataFrame(dict(A=[2,6,np.nan,9,9],\n",
 88 |     "                       B=[2,2,np.nan,5,5], \n",
 89 |     "                       C=[3,2,3,6,np.nan]))\n",
 90 |     "df"
 91 |    ]
 92 |   },
 93 |   {
 94 |    "cell_type": "code",
 95 |    "execution_count": 7,
 96 |    "id": "b302cb0a",
 97 |    "metadata": {},
 98 |    "outputs": [
 99 |     {
100 |      "data": {
101 |       "text/html": [
102 |        "<div>\n",
103 |        "<style scoped>\n",
104 |        "    .dataframe tbody tr th:only-of-type {\n",
105 |        "        vertical-align: middle;\n",
106 |        "    }\n",
107 |        "\n",
108 |        "    .dataframe tbody tr th {\n",
109 |        "        vertical-align: top;\n",
110 |        "    }\n",
111 |        "\n",
112 |        "    .dataframe thead th {\n",
113 |        "        text-align: right;\n",
114 |        "    }\n",
115 |        "</style>\n",
116 |        "<table border=\"1\" class=\"dataframe\">\n",
117 |        "  <thead>\n",
118 |        "    <tr style=\"text-align: right;\">\n",
119 |        "      <th></th>\n",
120 |        "      <th>A</th>\n",
121 |        "      <th>B</th>\n",
122 |        "      <th>C</th>\n",
123 |        "    </tr>\n",
124 |        "  </thead>\n",
125 |        "  <tbody>\n",
126 |        "    <tr>\n",
127 |        "      <th>3</th>\n",
128 |        "      <td>9.0</td>\n",
129 |        "      <td>5.0</td>\n",
130 |        "      <td>6.0</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>4</th>\n",
134 |        "      <td>9.0</td>\n",
135 |        "      <td>5.0</td>\n",
136 |        "      <td>NaN</td>\n",
137 |        "    </tr>\n",
138 |        "  </tbody>\n",
139 |        "</table>\n",
140 |        "</div>"
141 |       ],
142 |       "text/plain": [
143 |        "     A    B    C\n",
144 |        "3  9.0  5.0  6.0\n",
145 |        "4  9.0  5.0  NaN"
146 |       ]
147 |      },
148 |      "execution_count": 7,
149 |      "metadata": {},
150 |      "output_type": "execute_result"
151 |     }
152 |    ],
153 |    "source": [
154 |     "dfg = df.groupby([\"A\",\"B\"])\n",
155 |     "dfg.get_group((9,5))"
156 |    ]
157 |   },
158 |   {
159 |    "cell_type": "code",
160 |    "execution_count": 8,
161 |    "id": "1a3e5165",
162 |    "metadata": {},
163 |    "outputs": [
164 |     {
165 |      "data": {
166 |       "text/html": [
167 |        "<div>\n",
168 |        "<style scoped>\n",
169 |        "    .dataframe tbody tr th:only-of-type {\n",
170 |        "        vertical-align: middle;\n",
171 |        "    }\n",
172 |        "\n",
173 |        "    .dataframe tbody tr th {\n",
174 |        "        vertical-align: top;\n",
175 |        "    }\n",
176 |        "\n",
177 |        "    .dataframe thead th {\n",
178 |        "        text-align: right;\n",
179 |        "    }\n",
180 |        "</style>\n",
181 |        "<table border=\"1\" class=\"dataframe\">\n",
182 |        "  <thead>\n",
183 |        "    <tr style=\"text-align: right;\">\n",
184 |        "      <th></th>\n",
185 |        "      <th>A</th>\n",
186 |        "      <th>B</th>\n",
187 |        "      <th>C</th>\n",
188 |        "    </tr>\n",
189 |        "  </thead>\n",
190 |        "  <tbody>\n",
191 |        "    <tr>\n",
192 |        "      <th>3</th>\n",
193 |        "      <td>9.0</td>\n",
194 |        "      <td>5.0</td>\n",
195 |        "      <td>6.0</td>\n",
196 |        "    </tr>\n",
197 |        "    <tr>\n",
198 |        "      <th>4</th>\n",
199 |        "      <td>9.0</td>\n",
200 |        "      <td>5.0</td>\n",
201 |        "      <td>NaN</td>\n",
202 |        "    </tr>\n",
203 |        "  </tbody>\n",
204 |        "</table>\n",
205 |        "</div>"
206 |       ],
207 |       "text/plain": [
208 |        "     A    B    C\n",
209 |        "3  9.0  5.0  6.0\n",
210 |        "4  9.0  5.0  NaN"
211 |       ]
212 |      },
213 |      "execution_count": 8,
214 |      "metadata": {},
215 |      "output_type": "execute_result"
216 |     }
217 |    ],
218 |    "source": [
219 |     "df[(df[\"A\"]==9)&(df[\"B\"]==5)]"
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "code",
224 |    "execution_count": null,
225 |    "id": "fff668db",
226 |    "metadata": {},
227 |    "outputs": [],
228 |    "source": []
229 |   }
230 |  ],
231 |  "metadata": {
232 |   "kernelspec": {
233 |    "display_name": "Python 3 (ipykernel)",
234 |    "language": "python",
235 |    "name": "python3"
236 |   },
237 |   "language_info": {
238 |    "codemirror_mode": {
239 |     "name": "ipython",
240 |     "version": 3
241 |    },
242 |    "file_extension": ".py",
243 |    "mimetype": "text/x-python",
244 |    "name": "python",
245 |    "nbconvert_exporter": "python",
246 |    "pygments_lexer": "ipython3",
247 |    "version": "3.9.13"
248 |   }
249 |  },
250 |  "nbformat": 4,
251 |  "nbformat_minor": 5
252 | }
253 | 


--------------------------------------------------------------------------------
/Session1/get rid of Unnamed in df.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 4,
  6 |    "id": "e2491e65",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>Unnamed: 0</th>\n",
 31 |        "      <th>A</th>\n",
 32 |        "      <th>B</th>\n",
 33 |        "      <th>C</th>\n",
 34 |        "    </tr>\n",
 35 |        "  </thead>\n",
 36 |        "  <tbody>\n",
 37 |        "    <tr>\n",
 38 |        "      <th>0</th>\n",
 39 |        "      <td>0</td>\n",
 40 |        "      <td>2</td>\n",
 41 |        "      <td>2</td>\n",
 42 |        "      <td>3</td>\n",
 43 |        "    </tr>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>1</th>\n",
 46 |        "      <td>1</td>\n",
 47 |        "      <td>6</td>\n",
 48 |        "      <td>2</td>\n",
 49 |        "      <td>2</td>\n",
 50 |        "    </tr>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>2</th>\n",
 53 |        "      <td>2</td>\n",
 54 |        "      <td>3</td>\n",
 55 |        "      <td>6</td>\n",
 56 |        "      <td>3</td>\n",
 57 |        "    </tr>\n",
 58 |        "  </tbody>\n",
 59 |        "</table>\n",
 60 |        "</div>"
 61 |       ],
 62 |       "text/plain": [
 63 |        "   Unnamed: 0  A  B  C\n",
 64 |        "0           0  2  2  3\n",
 65 |        "1           1  6  2  2\n",
 66 |        "2           2  3  6  3"
 67 |       ]
 68 |      },
 69 |      "execution_count": 4,
 70 |      "metadata": {},
 71 |      "output_type": "execute_result"
 72 |     }
 73 |    ],
 74 |    "source": [
 75 |     "import pandas as pd\n",
 76 |     "df = pd.DataFrame(dict(A=[2,6,3],\n",
 77 |     "                       B=[2,2,6], \n",
 78 |     "                       C=[3,2,3]))\n",
 79 |     "df.to_csv(\"datas.csv\")\n",
 80 |     "\n",
 81 |     "df = pd.read_csv(\"datas.csv\")\n",
 82 |     "df\n"
 83 |    ]
 84 |   },
 85 |   {
 86 |    "cell_type": "code",
 87 |    "execution_count": 9,
 88 |    "id": "e2087034",
 89 |    "metadata": {},
 90 |    "outputs": [
 91 |     {
 92 |      "data": {
 93 |       "text/html": [
 94 |        "<div>\n",
 95 |        "<style scoped>\n",
 96 |        "    .dataframe tbody tr th:only-of-type {\n",
 97 |        "        vertical-align: middle;\n",
 98 |        "    }\n",
 99 |        "\n",
100 |        "    .dataframe tbody tr th {\n",
101 |        "        vertical-align: top;\n",
102 |        "    }\n",
103 |        "\n",
104 |        "    .dataframe thead th {\n",
105 |        "        text-align: right;\n",
106 |        "    }\n",
107 |        "</style>\n",
108 |        "<table border=\"1\" class=\"dataframe\">\n",
109 |        "  <thead>\n",
110 |        "    <tr style=\"text-align: right;\">\n",
111 |        "      <th></th>\n",
112 |        "      <th>A</th>\n",
113 |        "      <th>B</th>\n",
114 |        "      <th>C</th>\n",
115 |        "    </tr>\n",
116 |        "  </thead>\n",
117 |        "  <tbody>\n",
118 |        "    <tr>\n",
119 |        "      <th>0</th>\n",
120 |        "      <td>2</td>\n",
121 |        "      <td>2</td>\n",
122 |        "      <td>3</td>\n",
123 |        "    </tr>\n",
124 |        "    <tr>\n",
125 |        "      <th>1</th>\n",
126 |        "      <td>6</td>\n",
127 |        "      <td>2</td>\n",
128 |        "      <td>2</td>\n",
129 |        "    </tr>\n",
130 |        "    <tr>\n",
131 |        "      <th>2</th>\n",
132 |        "      <td>3</td>\n",
133 |        "      <td>6</td>\n",
134 |        "      <td>3</td>\n",
135 |        "    </tr>\n",
136 |        "  </tbody>\n",
137 |        "</table>\n",
138 |        "</div>"
139 |       ],
140 |       "text/plain": [
141 |        "   A  B  C\n",
142 |        "0  2  2  3\n",
143 |        "1  6  2  2\n",
144 |        "2  3  6  3"
145 |       ]
146 |      },
147 |      "execution_count": 9,
148 |      "metadata": {},
149 |      "output_type": "execute_result"
150 |     }
151 |    ],
152 |    "source": [
153 |     "df = pd.read_csv(\"datas.csv\", index_col=0)\n",
154 |     "df"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": null,
160 |    "id": "49edc69c",
161 |    "metadata": {},
162 |    "outputs": [],
163 |    "source": []
164 |   }
165 |  ],
166 |  "metadata": {
167 |   "kernelspec": {
168 |    "display_name": "Python 3 (ipykernel)",
169 |    "language": "python",
170 |    "name": "python3"
171 |   },
172 |   "language_info": {
173 |    "codemirror_mode": {
174 |     "name": "ipython",
175 |     "version": 3
176 |    },
177 |    "file_extension": ".py",
178 |    "mimetype": "text/x-python",
179 |    "name": "python",
180 |    "nbconvert_exporter": "python",
181 |    "pygments_lexer": "ipython3",
182 |    "version": "3.9.13"
183 |   }
184 |  },
185 |  "nbformat": 4,
186 |  "nbformat_minor": 5
187 | }
188 | 


--------------------------------------------------------------------------------
/Session1/groupby agg multindex drop level.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "d4e8e00b",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>A</th>\n",
 31 |        "      <th>B</th>\n",
 32 |        "      <th>C</th>\n",
 33 |        "      <th>D</th>\n",
 34 |        "    </tr>\n",
 35 |        "  </thead>\n",
 36 |        "  <tbody>\n",
 37 |        "    <tr>\n",
 38 |        "      <th>0</th>\n",
 39 |        "      <td>15</td>\n",
 40 |        "      <td>20</td>\n",
 41 |        "      <td>30</td>\n",
 42 |        "      <td>50</td>\n",
 43 |        "    </tr>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>1</th>\n",
 46 |        "      <td>20</td>\n",
 47 |        "      <td>25</td>\n",
 48 |        "      <td>40</td>\n",
 49 |        "      <td>60</td>\n",
 50 |        "    </tr>\n",
 51 |        "  </tbody>\n",
 52 |        "</table>\n",
 53 |        "</div>"
 54 |       ],
 55 |       "text/plain": [
 56 |        "    A   B   C   D\n",
 57 |        "0  15  20  30  50\n",
 58 |        "1  20  25  40  60"
 59 |       ]
 60 |      },
 61 |      "execution_count": 1,
 62 |      "metadata": {},
 63 |      "output_type": "execute_result"
 64 |     }
 65 |    ],
 66 |    "source": [
 67 |     "import pandas as pd\n",
 68 |     "d = {\"A\":[15, 20], \"B\":[20, 25], \"C\":[30 ,40], \"D\":[50, 60]}\n",
 69 |     "df = pd.DataFrame(d)\n",
 70 |     "df"
 71 |    ]
 72 |   },
 73 |   {
 74 |    "cell_type": "code",
 75 |    "execution_count": 2,
 76 |    "id": "abc8e804",
 77 |    "metadata": {},
 78 |    "outputs": [
 79 |     {
 80 |      "name": "stdout",
 81 |      "output_type": "stream",
 82 |      "text": [
 83 |       "The Problem relies on that we don't know the column name\n"
 84 |      ]
 85 |     },
 86 |     {
 87 |      "data": {
 88 |       "text/html": [
 89 |        "<div>\n",
 90 |        "<style scoped>\n",
 91 |        "    .dataframe tbody tr th:only-of-type {\n",
 92 |        "        vertical-align: middle;\n",
 93 |        "    }\n",
 94 |        "\n",
 95 |        "    .dataframe tbody tr th {\n",
 96 |        "        vertical-align: top;\n",
 97 |        "    }\n",
 98 |        "\n",
 99 |        "    .dataframe thead th {\n",
100 |        "        text-align: right;\n",
101 |        "    }\n",
102 |        "</style>\n",
103 |        "<table border=\"1\" class=\"dataframe\">\n",
104 |        "  <thead>\n",
105 |        "    <tr style=\"text-align: right;\">\n",
106 |        "      <th></th>\n",
107 |        "      <th>mean</th>\n",
108 |        "      <th>max</th>\n",
109 |        "    </tr>\n",
110 |        "    <tr>\n",
111 |        "      <th>A</th>\n",
112 |        "      <th></th>\n",
113 |        "      <th></th>\n",
114 |        "    </tr>\n",
115 |        "  </thead>\n",
116 |        "  <tbody>\n",
117 |        "    <tr>\n",
118 |        "      <th>15</th>\n",
119 |        "      <td>20.0</td>\n",
120 |        "      <td>20</td>\n",
121 |        "    </tr>\n",
122 |        "    <tr>\n",
123 |        "      <th>20</th>\n",
124 |        "      <td>25.0</td>\n",
125 |        "      <td>25</td>\n",
126 |        "    </tr>\n",
127 |        "  </tbody>\n",
128 |        "</table>\n",
129 |        "</div>"
130 |       ],
131 |       "text/plain": [
132 |        "    mean  max\n",
133 |        "A            \n",
134 |        "15  20.0   20\n",
135 |        "20  25.0   25"
136 |       ]
137 |      },
138 |      "execution_count": 2,
139 |      "metadata": {},
140 |      "output_type": "execute_result"
141 |     }
142 |    ],
143 |    "source": [
144 |     "print(\"The Problem relies on that we don't know the column name\")\n",
145 |     "df.groupby(\"A\")[\"B\"].agg([\"mean\", \"max\"])"
146 |    ]
147 |   },
148 |   {
149 |    "cell_type": "code",
150 |    "execution_count": 3,
151 |    "id": "b89eee03",
152 |    "metadata": {},
153 |    "outputs": [
154 |     {
155 |      "name": "stdout",
156 |      "output_type": "stream",
157 |      "text": [
158 |       "The Problem relies on that we have multiindex\n"
159 |      ]
160 |     },
161 |     {
162 |      "data": {
163 |       "text/html": [
164 |        "<div>\n",
165 |        "<style scoped>\n",
166 |        "    .dataframe tbody tr th:only-of-type {\n",
167 |        "        vertical-align: middle;\n",
168 |        "    }\n",
169 |        "\n",
170 |        "    .dataframe tbody tr th {\n",
171 |        "        vertical-align: top;\n",
172 |        "    }\n",
173 |        "\n",
174 |        "    .dataframe thead tr th {\n",
175 |        "        text-align: left;\n",
176 |        "    }\n",
177 |        "\n",
178 |        "    .dataframe thead tr:last-of-type th {\n",
179 |        "        text-align: right;\n",
180 |        "    }\n",
181 |        "</style>\n",
182 |        "<table border=\"1\" class=\"dataframe\">\n",
183 |        "  <thead>\n",
184 |        "    <tr>\n",
185 |        "      <th></th>\n",
186 |        "      <th colspan=\"2\" halign=\"left\">B</th>\n",
187 |        "    </tr>\n",
188 |        "    <tr>\n",
189 |        "      <th></th>\n",
190 |        "      <th>mean</th>\n",
191 |        "      <th>max</th>\n",
192 |        "    </tr>\n",
193 |        "    <tr>\n",
194 |        "      <th>A</th>\n",
195 |        "      <th></th>\n",
196 |        "      <th></th>\n",
197 |        "    </tr>\n",
198 |        "  </thead>\n",
199 |        "  <tbody>\n",
200 |        "    <tr>\n",
201 |        "      <th>15</th>\n",
202 |        "      <td>20.0</td>\n",
203 |        "      <td>20</td>\n",
204 |        "    </tr>\n",
205 |        "    <tr>\n",
206 |        "      <th>20</th>\n",
207 |        "      <td>25.0</td>\n",
208 |        "      <td>25</td>\n",
209 |        "    </tr>\n",
210 |        "  </tbody>\n",
211 |        "</table>\n",
212 |        "</div>"
213 |       ],
214 |       "text/plain": [
215 |        "       B    \n",
216 |        "    mean max\n",
217 |        "A           \n",
218 |        "15  20.0  20\n",
219 |        "20  25.0  25"
220 |       ]
221 |      },
222 |      "execution_count": 3,
223 |      "metadata": {},
224 |      "output_type": "execute_result"
225 |     }
226 |    ],
227 |    "source": [
228 |     "print(\"The Problem relies on that we have multiindex\")\n",
229 |     "df.groupby(\"A\").agg({\"B\":[\"mean\", \"max\"]}) # .columns.droplevel()"
230 |    ]
231 |   },
232 |   {
233 |    "cell_type": "code",
234 |    "execution_count": 4,
235 |    "id": "c6b0212c",
236 |    "metadata": {},
237 |    "outputs": [
238 |     {
239 |      "data": {
240 |       "text/html": [
241 |        "<div>\n",
242 |        "<style scoped>\n",
243 |        "    .dataframe tbody tr th:only-of-type {\n",
244 |        "        vertical-align: middle;\n",
245 |        "    }\n",
246 |        "\n",
247 |        "    .dataframe tbody tr th {\n",
248 |        "        vertical-align: top;\n",
249 |        "    }\n",
250 |        "\n",
251 |        "    .dataframe thead th {\n",
252 |        "        text-align: right;\n",
253 |        "    }\n",
254 |        "</style>\n",
255 |        "<table border=\"1\" class=\"dataframe\">\n",
256 |        "  <thead>\n",
257 |        "    <tr style=\"text-align: right;\">\n",
258 |        "      <th></th>\n",
259 |        "      <th>A_mean</th>\n",
260 |        "      <th>A_max</th>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>A</th>\n",
264 |        "      <th></th>\n",
265 |        "      <th></th>\n",
266 |        "    </tr>\n",
267 |        "  </thead>\n",
268 |        "  <tbody>\n",
269 |        "    <tr>\n",
270 |        "      <th>15</th>\n",
271 |        "      <td>20.0</td>\n",
272 |        "      <td>20</td>\n",
273 |        "    </tr>\n",
274 |        "    <tr>\n",
275 |        "      <th>20</th>\n",
276 |        "      <td>25.0</td>\n",
277 |        "      <td>25</td>\n",
278 |        "    </tr>\n",
279 |        "  </tbody>\n",
280 |        "</table>\n",
281 |        "</div>"
282 |       ],
283 |       "text/plain": [
284 |        "    A_mean  A_max\n",
285 |        "A                \n",
286 |        "15    20.0     20\n",
287 |        "20    25.0     25"
288 |       ]
289 |      },
290 |      "execution_count": 4,
291 |      "metadata": {},
292 |      "output_type": "execute_result"
293 |     }
294 |    ],
295 |    "source": [
296 |     "df.groupby(\"A\")[\"B\"].agg(A_mean = \"mean\", A_max = \"max\")"
297 |    ]
298 |   },
299 |   {
300 |    "cell_type": "code",
301 |    "execution_count": null,
302 |    "id": "a2f7aa57",
303 |    "metadata": {},
304 |    "outputs": [],
305 |    "source": []
306 |   }
307 |  ],
308 |  "metadata": {
309 |   "kernelspec": {
310 |    "display_name": "Python 3 (ipykernel)",
311 |    "language": "python",
312 |    "name": "python3"
313 |   },
314 |   "language_info": {
315 |    "codemirror_mode": {
316 |     "name": "ipython",
317 |     "version": 3
318 |    },
319 |    "file_extension": ".py",
320 |    "mimetype": "text/x-python",
321 |    "name": "python",
322 |    "nbconvert_exporter": "python",
323 |    "pygments_lexer": "ipython3",
324 |    "version": "3.9.13"
325 |   }
326 |  },
327 |  "nbformat": 4,
328 |  "nbformat_minor": 5
329 | }
330 | 


--------------------------------------------------------------------------------
/Session1/insert and change column order in pandas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 22,
  6 |    "id": "894283de",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>A</th>\n",
 31 |        "      <th>B</th>\n",
 32 |        "      <th>C</th>\n",
 33 |        "      <th>D</th>\n",
 34 |        "    </tr>\n",
 35 |        "  </thead>\n",
 36 |        "  <tbody>\n",
 37 |        "    <tr>\n",
 38 |        "      <th>0</th>\n",
 39 |        "      <td>15</td>\n",
 40 |        "      <td>20</td>\n",
 41 |        "      <td>30</td>\n",
 42 |        "      <td>50</td>\n",
 43 |        "    </tr>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>1</th>\n",
 46 |        "      <td>20</td>\n",
 47 |        "      <td>25</td>\n",
 48 |        "      <td>40</td>\n",
 49 |        "      <td>60</td>\n",
 50 |        "    </tr>\n",
 51 |        "  </tbody>\n",
 52 |        "</table>\n",
 53 |        "</div>"
 54 |       ],
 55 |       "text/plain": [
 56 |        "    A   B   C   D\n",
 57 |        "0  15  20  30  50\n",
 58 |        "1  20  25  40  60"
 59 |       ]
 60 |      },
 61 |      "execution_count": 22,
 62 |      "metadata": {},
 63 |      "output_type": "execute_result"
 64 |     }
 65 |    ],
 66 |    "source": [
 67 |     "import pandas as pd\n",
 68 |     "d = {\"A\":[15, 20], \"B\":[20, 25], \"C\":[30 ,40], \"D\":[50, 60]}\n",
 69 |     "df = pd.DataFrame(d)\n",
 70 |     "df"
 71 |    ]
 72 |   },
 73 |   {
 74 |    "cell_type": "code",
 75 |    "execution_count": 14,
 76 |    "id": "8ceaf614",
 77 |    "metadata": {},
 78 |    "outputs": [
 79 |     {
 80 |      "data": {
 81 |       "text/html": [
 82 |        "<div>\n",
 83 |        "<style scoped>\n",
 84 |        "    .dataframe tbody tr th:only-of-type {\n",
 85 |        "        vertical-align: middle;\n",
 86 |        "    }\n",
 87 |        "\n",
 88 |        "    .dataframe tbody tr th {\n",
 89 |        "        vertical-align: top;\n",
 90 |        "    }\n",
 91 |        "\n",
 92 |        "    .dataframe thead th {\n",
 93 |        "        text-align: right;\n",
 94 |        "    }\n",
 95 |        "</style>\n",
 96 |        "<table border=\"1\" class=\"dataframe\">\n",
 97 |        "  <thead>\n",
 98 |        "    <tr style=\"text-align: right;\">\n",
 99 |        "      <th></th>\n",
100 |        "      <th>A</th>\n",
101 |        "      <th>B</th>\n",
102 |        "      <th>C</th>\n",
103 |        "      <th>C2</th>\n",
104 |        "      <th>D</th>\n",
105 |        "    </tr>\n",
106 |        "  </thead>\n",
107 |        "  <tbody>\n",
108 |        "    <tr>\n",
109 |        "      <th>0</th>\n",
110 |        "      <td>15</td>\n",
111 |        "      <td>20</td>\n",
112 |        "      <td>30</td>\n",
113 |        "      <td>60</td>\n",
114 |        "      <td>50</td>\n",
115 |        "    </tr>\n",
116 |        "    <tr>\n",
117 |        "      <th>1</th>\n",
118 |        "      <td>20</td>\n",
119 |        "      <td>25</td>\n",
120 |        "      <td>40</td>\n",
121 |        "      <td>80</td>\n",
122 |        "      <td>60</td>\n",
123 |        "    </tr>\n",
124 |        "  </tbody>\n",
125 |        "</table>\n",
126 |        "</div>"
127 |       ],
128 |       "text/plain": [
129 |        "    A   B   C  C2   D\n",
130 |        "0  15  20  30  60  50\n",
131 |        "1  20  25  40  80  60"
132 |       ]
133 |      },
134 |      "execution_count": 14,
135 |      "metadata": {},
136 |      "output_type": "execute_result"
137 |     }
138 |    ],
139 |    "source": [
140 |     "# Using insert\n",
141 |     "df.insert(3, \"C2\", df[\"C\"]*2)\n",
142 |     "df"
143 |    ]
144 |   },
145 |   {
146 |    "cell_type": "code",
147 |    "execution_count": 8,
148 |    "id": "c0bb34d2",
149 |    "metadata": {},
150 |    "outputs": [
151 |     {
152 |      "data": {
153 |       "text/html": [
154 |        "<div>\n",
155 |        "<style scoped>\n",
156 |        "    .dataframe tbody tr th:only-of-type {\n",
157 |        "        vertical-align: middle;\n",
158 |        "    }\n",
159 |        "\n",
160 |        "    .dataframe tbody tr th {\n",
161 |        "        vertical-align: top;\n",
162 |        "    }\n",
163 |        "\n",
164 |        "    .dataframe thead th {\n",
165 |        "        text-align: right;\n",
166 |        "    }\n",
167 |        "</style>\n",
168 |        "<table border=\"1\" class=\"dataframe\">\n",
169 |        "  <thead>\n",
170 |        "    <tr style=\"text-align: right;\">\n",
171 |        "      <th></th>\n",
172 |        "      <th>A</th>\n",
173 |        "      <th>B</th>\n",
174 |        "      <th>C2</th>\n",
175 |        "      <th>D</th>\n",
176 |        "      <th>C</th>\n",
177 |        "    </tr>\n",
178 |        "  </thead>\n",
179 |        "  <tbody>\n",
180 |        "    <tr>\n",
181 |        "      <th>0</th>\n",
182 |        "      <td>15</td>\n",
183 |        "      <td>20</td>\n",
184 |        "      <td>60</td>\n",
185 |        "      <td>50</td>\n",
186 |        "      <td>30</td>\n",
187 |        "    </tr>\n",
188 |        "    <tr>\n",
189 |        "      <th>1</th>\n",
190 |        "      <td>20</td>\n",
191 |        "      <td>25</td>\n",
192 |        "      <td>80</td>\n",
193 |        "      <td>60</td>\n",
194 |        "      <td>40</td>\n",
195 |        "    </tr>\n",
196 |        "  </tbody>\n",
197 |        "</table>\n",
198 |        "</div>"
199 |       ],
200 |       "text/plain": [
201 |        "    A   B  C2   D   C\n",
202 |        "0  15  20  60  50  30\n",
203 |        "1  20  25  80  60  40"
204 |       ]
205 |      },
206 |      "execution_count": 8,
207 |      "metadata": {},
208 |      "output_type": "execute_result"
209 |     }
210 |    ],
211 |    "source": [
212 |     "col_num = 2\n",
213 |     "df.iloc[:,[i for i in range(df.shape[1]) if i!=col_num] + [col_num]]"
214 |    ]
215 |   },
216 |   {
217 |    "cell_type": "code",
218 |    "execution_count": 9,
219 |    "id": "8b005c59",
220 |    "metadata": {},
221 |    "outputs": [
222 |     {
223 |      "data": {
224 |       "text/plain": [
225 |        "[0, 1, 3, 4, 2]"
226 |       ]
227 |      },
228 |      "execution_count": 9,
229 |      "metadata": {},
230 |      "output_type": "execute_result"
231 |     }
232 |    ],
233 |    "source": [
234 |     "[i for i in range(df.shape[1]) if i!=col_num] + [col_num]"
235 |    ]
236 |   },
237 |   {
238 |    "cell_type": "code",
239 |    "execution_count": null,
240 |    "id": "757068d1",
241 |    "metadata": {},
242 |    "outputs": [],
243 |    "source": []
244 |   }
245 |  ],
246 |  "metadata": {
247 |   "kernelspec": {
248 |    "display_name": "Python 3 (ipykernel)",
249 |    "language": "python",
250 |    "name": "python3"
251 |   },
252 |   "language_info": {
253 |    "codemirror_mode": {
254 |     "name": "ipython",
255 |     "version": 3
256 |    },
257 |    "file_extension": ".py",
258 |    "mimetype": "text/x-python",
259 |    "name": "python",
260 |    "nbconvert_exporter": "python",
261 |    "pygments_lexer": "ipython3",
262 |    "version": "3.9.13"
263 |   }
264 |  },
265 |  "nbformat": 4,
266 |  "nbformat_minor": 5
267 | }
268 | 


--------------------------------------------------------------------------------
/Session1/regex eliminate string and convert string to float.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 4,
  6 |    "id": "8f94fb2e",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>customer</th>\n",
 31 |        "      <th>sales</th>\n",
 32 |        "    </tr>\n",
 33 |        "  </thead>\n",
 34 |        "  <tbody>\n",
 35 |        "    <tr>\n",
 36 |        "      <th>0</th>\n",
 37 |        "      <td>A</td>\n",
 38 |        "      <td>1100</td>\n",
 39 |        "    </tr>\n",
 40 |        "    <tr>\n",
 41 |        "      <th>1</th>\n",
 42 |        "      <td>B</td>\n",
 43 |        "      <td>950.75</td>\n",
 44 |        "    </tr>\n",
 45 |        "    <tr>\n",
 46 |        "      <th>2</th>\n",
 47 |        "      <td>C</td>\n",
 48 |        "      <td>$$$-400</td>\n",
 49 |        "    </tr>\n",
 50 |        "    <tr>\n",
 51 |        "      <th>3</th>\n",
 52 |        "      <td>D</td>\n",
 53 |        "      <td>$1250.35*</td>\n",
 54 |        "    </tr>\n",
 55 |        "  </tbody>\n",
 56 |        "</table>\n",
 57 |        "</div>"
 58 |       ],
 59 |       "text/plain": [
 60 |        "  customer      sales\n",
 61 |        "0        A       1100\n",
 62 |        "1        B     950.75\n",
 63 |        "2        C    $$$-400\n",
 64 |        "3        D  $1250.35*"
 65 |       ]
 66 |      },
 67 |      "execution_count": 4,
 68 |      "metadata": {},
 69 |      "output_type": "execute_result"
 70 |     }
 71 |    ],
 72 |    "source": [
 73 |     "import pandas as pd \n",
 74 |     "d = {\"customer\": [\"A\", \"B\", \"C\", \"D\"], \"sales\":[1100, 950.75, \"$$$-400\", \"$1250.35*\"]}\n",
 75 |     "df = pd.DataFrame(d)\n",
 76 |     "df\n",
 77 |     "\n"
 78 |    ]
 79 |   },
 80 |   {
 81 |    "cell_type": "code",
 82 |    "execution_count": 42,
 83 |    "id": "4ecbe5ce",
 84 |    "metadata": {},
 85 |    "outputs": [
 86 |     {
 87 |      "data": {
 88 |       "text/plain": [
 89 |        "0      <class 'int'>\n",
 90 |        "1    <class 'float'>\n",
 91 |        "2      <class 'str'>\n",
 92 |        "3      <class 'str'>\n",
 93 |        "Name: sales, dtype: object"
 94 |       ]
 95 |      },
 96 |      "execution_count": 42,
 97 |      "metadata": {},
 98 |      "output_type": "execute_result"
 99 |     }
100 |    ],
101 |    "source": [
102 |     "# Step 1: check the data types\n",
103 |     "df[\"sales\"].apply(type)"
104 |    ]
105 |   },
106 |   {
107 |    "cell_type": "code",
108 |    "execution_count": 2,
109 |    "id": "c01ba1a5",
110 |    "metadata": {},
111 |    "outputs": [
112 |     {
113 |      "data": {
114 |       "text/html": [
115 |        "<div>\n",
116 |        "<style scoped>\n",
117 |        "    .dataframe tbody tr th:only-of-type {\n",
118 |        "        vertical-align: middle;\n",
119 |        "    }\n",
120 |        "\n",
121 |        "    .dataframe tbody tr th {\n",
122 |        "        vertical-align: top;\n",
123 |        "    }\n",
124 |        "\n",
125 |        "    .dataframe thead th {\n",
126 |        "        text-align: right;\n",
127 |        "    }\n",
128 |        "</style>\n",
129 |        "<table border=\"1\" class=\"dataframe\">\n",
130 |        "  <thead>\n",
131 |        "    <tr style=\"text-align: right;\">\n",
132 |        "      <th></th>\n",
133 |        "      <th>customer</th>\n",
134 |        "      <th>sales</th>\n",
135 |        "    </tr>\n",
136 |        "  </thead>\n",
137 |        "  <tbody>\n",
138 |        "    <tr>\n",
139 |        "      <th>0</th>\n",
140 |        "      <td>A</td>\n",
141 |        "      <td>1100.00</td>\n",
142 |        "    </tr>\n",
143 |        "    <tr>\n",
144 |        "      <th>1</th>\n",
145 |        "      <td>B</td>\n",
146 |        "      <td>950.75</td>\n",
147 |        "    </tr>\n",
148 |        "    <tr>\n",
149 |        "      <th>2</th>\n",
150 |        "      <td>C</td>\n",
151 |        "      <td>400.00</td>\n",
152 |        "    </tr>\n",
153 |        "    <tr>\n",
154 |        "      <th>3</th>\n",
155 |        "      <td>D</td>\n",
156 |        "      <td>1250.35</td>\n",
157 |        "    </tr>\n",
158 |        "  </tbody>\n",
159 |        "</table>\n",
160 |        "</div>"
161 |       ],
162 |       "text/plain": [
163 |        "  customer    sales\n",
164 |        "0        A  1100.00\n",
165 |        "1        B   950.75\n",
166 |        "2        C   400.00\n",
167 |        "3        D  1250.35"
168 |       ]
169 |      },
170 |      "execution_count": 2,
171 |      "metadata": {},
172 |      "output_type": "execute_result"
173 |     }
174 |    ],
175 |    "source": [
176 |     "# Step 2: use regex\n",
177 |     "df[\"sales\"] = df[\"sales\"].replace(\"[$\\-\\_\\*]\", \"\", regex = True).astype(\"float\")\n",
178 |     "df"
179 |    ]
180 |   },
181 |   {
182 |    "cell_type": "code",
183 |    "execution_count": 5,
184 |    "id": "ccfecc45",
185 |    "metadata": {},
186 |    "outputs": [
187 |     {
188 |      "data": {
189 |       "text/plain": [
190 |        "0        NaN\n",
191 |        "1        NaN\n",
192 |        "2    -400.00\n",
193 |        "3    1250.35\n",
194 |        "Name: sales, dtype: float64"
195 |       ]
196 |      },
197 |      "execution_count": 5,
198 |      "metadata": {},
199 |      "output_type": "execute_result"
200 |     }
201 |    ],
202 |    "source": [
203 |     "df[\"sales\"].str.strip(\"$*\").astype(\"float\")"
204 |    ]
205 |   },
206 |   {
207 |    "cell_type": "code",
208 |    "execution_count": null,
209 |    "id": "62825311",
210 |    "metadata": {},
211 |    "outputs": [],
212 |    "source": []
213 |   }
214 |  ],
215 |  "metadata": {
216 |   "kernelspec": {
217 |    "display_name": "Python 3 (ipykernel)",
218 |    "language": "python",
219 |    "name": "python3"
220 |   },
221 |   "language_info": {
222 |    "codemirror_mode": {
223 |     "name": "ipython",
224 |     "version": 3
225 |    },
226 |    "file_extension": ".py",
227 |    "mimetype": "text/x-python",
228 |    "name": "python",
229 |    "nbconvert_exporter": "python",
230 |    "pygments_lexer": "ipython3",
231 |    "version": "3.9.13"
232 |   }
233 |  },
234 |  "nbformat": 4,
235 |  "nbformat_minor": 5
236 | }
237 | 


--------------------------------------------------------------------------------
/Session2/If_Reads_Numerical_Values_As_Object_-_pandas.read_csv.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "51f838e1",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "markdown",
 15 |    "id": "5a5dadd3",
 16 |    "metadata": {},
 17 |    "source": [
 18 |     "example.csv\n",
 19 |     "\n",
 20 |     "0  |  100,000\n",
 21 |     "\n",
 22 |     "1  |  200,000\n",
 23 |     "\n",
 24 |     "2  |  300,000\n",
 25 |     "\n",
 26 |     "3  |  250,000\n",
 27 |     "\n",
 28 |     "If pandas reads "
 29 |    ]
 30 |   },
 31 |   {
 32 |    "cell_type": "code",
 33 |    "execution_count": 2,
 34 |    "id": "3d1b7fdf",
 35 |    "metadata": {},
 36 |    "outputs": [],
 37 |    "source": [
 38 |     "df = pd.read_csv(\"example.csv\", index_col = 0, thousands = \",\")"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 3,
 44 |    "id": "f65d2009",
 45 |    "metadata": {},
 46 |    "outputs": [
 47 |     {
 48 |      "data": {
 49 |       "text/html": [
 50 |        "<div>\n",
 51 |        "<style scoped>\n",
 52 |        "    .dataframe tbody tr th:only-of-type {\n",
 53 |        "        vertical-align: middle;\n",
 54 |        "    }\n",
 55 |        "\n",
 56 |        "    .dataframe tbody tr th {\n",
 57 |        "        vertical-align: top;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe thead th {\n",
 61 |        "        text-align: right;\n",
 62 |        "    }\n",
 63 |        "</style>\n",
 64 |        "<table border=\"1\" class=\"dataframe\">\n",
 65 |        "  <thead>\n",
 66 |        "    <tr style=\"text-align: right;\">\n",
 67 |        "      <th></th>\n",
 68 |        "      <th>0</th>\n",
 69 |        "    </tr>\n",
 70 |        "  </thead>\n",
 71 |        "  <tbody>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>0</th>\n",
 74 |        "      <td>100000</td>\n",
 75 |        "    </tr>\n",
 76 |        "    <tr>\n",
 77 |        "      <th>1</th>\n",
 78 |        "      <td>200000</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>2</th>\n",
 82 |        "      <td>300000</td>\n",
 83 |        "    </tr>\n",
 84 |        "    <tr>\n",
 85 |        "      <th>3</th>\n",
 86 |        "      <td>250000</td>\n",
 87 |        "    </tr>\n",
 88 |        "  </tbody>\n",
 89 |        "</table>\n",
 90 |        "</div>"
 91 |       ],
 92 |       "text/plain": [
 93 |        "        0\n",
 94 |        "0  100000\n",
 95 |        "1  200000\n",
 96 |        "2  300000\n",
 97 |        "3  250000"
 98 |       ]
 99 |      },
100 |      "execution_count": 3,
101 |      "metadata": {},
102 |      "output_type": "execute_result"
103 |     }
104 |    ],
105 |    "source": [
106 |     "df"
107 |    ]
108 |   },
109 |   {
110 |    "cell_type": "code",
111 |    "execution_count": 4,
112 |    "id": "09b31e28",
113 |    "metadata": {},
114 |    "outputs": [
115 |     {
116 |      "data": {
117 |       "text/plain": [
118 |        "0    int64\n",
119 |        "dtype: object"
120 |       ]
121 |      },
122 |      "execution_count": 4,
123 |      "metadata": {},
124 |      "output_type": "execute_result"
125 |     }
126 |    ],
127 |    "source": [
128 |     "df.dtypes"
129 |    ]
130 |   },
131 |   {
132 |    "cell_type": "code",
133 |    "execution_count": null,
134 |    "id": "e00a7d28",
135 |    "metadata": {},
136 |    "outputs": [],
137 |    "source": []
138 |   }
139 |  ],
140 |  "metadata": {
141 |   "kernelspec": {
142 |    "display_name": "Python 3 (ipykernel)",
143 |    "language": "python",
144 |    "name": "python3"
145 |   },
146 |   "language_info": {
147 |    "codemirror_mode": {
148 |     "name": "ipython",
149 |     "version": 3
150 |    },
151 |    "file_extension": ".py",
152 |    "mimetype": "text/x-python",
153 |    "name": "python",
154 |    "nbconvert_exporter": "python",
155 |    "pygments_lexer": "ipython3",
156 |    "version": "3.9.13"
157 |   }
158 |  },
159 |  "nbformat": 4,
160 |  "nbformat_minor": 5
161 | }
162 | 


--------------------------------------------------------------------------------
/Session2/Quick_One-Hot_Encoding_with_Pandas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "0364dbb2",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "cbc7d9dc",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "dummies = pd.DataFrame([\"A\", \"B\", \"A\", \"B\", \"C\"])"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 3,
 26 |    "id": "d73675e2",
 27 |    "metadata": {},
 28 |    "outputs": [
 29 |     {
 30 |      "data": {
 31 |       "text/html": [
 32 |        "<div>\n",
 33 |        "<style scoped>\n",
 34 |        "    .dataframe tbody tr th:only-of-type {\n",
 35 |        "        vertical-align: middle;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe tbody tr th {\n",
 39 |        "        vertical-align: top;\n",
 40 |        "    }\n",
 41 |        "\n",
 42 |        "    .dataframe thead th {\n",
 43 |        "        text-align: right;\n",
 44 |        "    }\n",
 45 |        "</style>\n",
 46 |        "<table border=\"1\" class=\"dataframe\">\n",
 47 |        "  <thead>\n",
 48 |        "    <tr style=\"text-align: right;\">\n",
 49 |        "      <th></th>\n",
 50 |        "      <th>0_A</th>\n",
 51 |        "      <th>0_B</th>\n",
 52 |        "      <th>0_C</th>\n",
 53 |        "    </tr>\n",
 54 |        "  </thead>\n",
 55 |        "  <tbody>\n",
 56 |        "    <tr>\n",
 57 |        "      <th>0</th>\n",
 58 |        "      <td>1</td>\n",
 59 |        "      <td>0</td>\n",
 60 |        "      <td>0</td>\n",
 61 |        "    </tr>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>1</th>\n",
 64 |        "      <td>0</td>\n",
 65 |        "      <td>1</td>\n",
 66 |        "      <td>0</td>\n",
 67 |        "    </tr>\n",
 68 |        "    <tr>\n",
 69 |        "      <th>2</th>\n",
 70 |        "      <td>1</td>\n",
 71 |        "      <td>0</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>3</th>\n",
 76 |        "      <td>0</td>\n",
 77 |        "      <td>1</td>\n",
 78 |        "      <td>0</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>4</th>\n",
 82 |        "      <td>0</td>\n",
 83 |        "      <td>0</td>\n",
 84 |        "      <td>1</td>\n",
 85 |        "    </tr>\n",
 86 |        "  </tbody>\n",
 87 |        "</table>\n",
 88 |        "</div>"
 89 |       ],
 90 |       "text/plain": [
 91 |        "   0_A  0_B  0_C\n",
 92 |        "0    1    0    0\n",
 93 |        "1    0    1    0\n",
 94 |        "2    1    0    0\n",
 95 |        "3    0    1    0\n",
 96 |        "4    0    0    1"
 97 |       ]
 98 |      },
 99 |      "execution_count": 3,
100 |      "metadata": {},
101 |      "output_type": "execute_result"
102 |     }
103 |    ],
104 |    "source": [
105 |     "pd.get_dummies(dummies)"
106 |    ]
107 |   },
108 |   {
109 |    "cell_type": "code",
110 |    "execution_count": 4,
111 |    "id": "18ede13c",
112 |    "metadata": {},
113 |    "outputs": [
114 |     {
115 |      "data": {
116 |       "text/html": [
117 |        "<div>\n",
118 |        "<style scoped>\n",
119 |        "    .dataframe tbody tr th:only-of-type {\n",
120 |        "        vertical-align: middle;\n",
121 |        "    }\n",
122 |        "\n",
123 |        "    .dataframe tbody tr th {\n",
124 |        "        vertical-align: top;\n",
125 |        "    }\n",
126 |        "\n",
127 |        "    .dataframe thead th {\n",
128 |        "        text-align: right;\n",
129 |        "    }\n",
130 |        "</style>\n",
131 |        "<table border=\"1\" class=\"dataframe\">\n",
132 |        "  <thead>\n",
133 |        "    <tr style=\"text-align: right;\">\n",
134 |        "      <th></th>\n",
135 |        "      <th>Dummy_A</th>\n",
136 |        "      <th>Dummy_B</th>\n",
137 |        "      <th>Dummy_C</th>\n",
138 |        "    </tr>\n",
139 |        "  </thead>\n",
140 |        "  <tbody>\n",
141 |        "    <tr>\n",
142 |        "      <th>0</th>\n",
143 |        "      <td>1</td>\n",
144 |        "      <td>0</td>\n",
145 |        "      <td>0</td>\n",
146 |        "    </tr>\n",
147 |        "    <tr>\n",
148 |        "      <th>1</th>\n",
149 |        "      <td>0</td>\n",
150 |        "      <td>1</td>\n",
151 |        "      <td>0</td>\n",
152 |        "    </tr>\n",
153 |        "    <tr>\n",
154 |        "      <th>2</th>\n",
155 |        "      <td>1</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>0</td>\n",
158 |        "    </tr>\n",
159 |        "    <tr>\n",
160 |        "      <th>3</th>\n",
161 |        "      <td>0</td>\n",
162 |        "      <td>1</td>\n",
163 |        "      <td>0</td>\n",
164 |        "    </tr>\n",
165 |        "    <tr>\n",
166 |        "      <th>4</th>\n",
167 |        "      <td>0</td>\n",
168 |        "      <td>0</td>\n",
169 |        "      <td>1</td>\n",
170 |        "    </tr>\n",
171 |        "  </tbody>\n",
172 |        "</table>\n",
173 |        "</div>"
174 |       ],
175 |       "text/plain": [
176 |        "   Dummy_A  Dummy_B  Dummy_C\n",
177 |        "0        1        0        0\n",
178 |        "1        0        1        0\n",
179 |        "2        1        0        0\n",
180 |        "3        0        1        0\n",
181 |        "4        0        0        1"
182 |       ]
183 |      },
184 |      "execution_count": 4,
185 |      "metadata": {},
186 |      "output_type": "execute_result"
187 |     }
188 |    ],
189 |    "source": [
190 |     "pd.get_dummies(dummies, prefix = \"Dummy\")"
191 |    ]
192 |   },
193 |   {
194 |    "cell_type": "code",
195 |    "execution_count": 5,
196 |    "id": "bb9739c5",
197 |    "metadata": {},
198 |    "outputs": [
199 |     {
200 |      "data": {
201 |       "text/html": [
202 |        "<div>\n",
203 |        "<style scoped>\n",
204 |        "    .dataframe tbody tr th:only-of-type {\n",
205 |        "        vertical-align: middle;\n",
206 |        "    }\n",
207 |        "\n",
208 |        "    .dataframe tbody tr th {\n",
209 |        "        vertical-align: top;\n",
210 |        "    }\n",
211 |        "\n",
212 |        "    .dataframe thead th {\n",
213 |        "        text-align: right;\n",
214 |        "    }\n",
215 |        "</style>\n",
216 |        "<table border=\"1\" class=\"dataframe\">\n",
217 |        "  <thead>\n",
218 |        "    <tr style=\"text-align: right;\">\n",
219 |        "      <th></th>\n",
220 |        "      <th>Dummy_B</th>\n",
221 |        "      <th>Dummy_C</th>\n",
222 |        "    </tr>\n",
223 |        "  </thead>\n",
224 |        "  <tbody>\n",
225 |        "    <tr>\n",
226 |        "      <th>0</th>\n",
227 |        "      <td>0</td>\n",
228 |        "      <td>0</td>\n",
229 |        "    </tr>\n",
230 |        "    <tr>\n",
231 |        "      <th>1</th>\n",
232 |        "      <td>1</td>\n",
233 |        "      <td>0</td>\n",
234 |        "    </tr>\n",
235 |        "    <tr>\n",
236 |        "      <th>2</th>\n",
237 |        "      <td>0</td>\n",
238 |        "      <td>0</td>\n",
239 |        "    </tr>\n",
240 |        "    <tr>\n",
241 |        "      <th>3</th>\n",
242 |        "      <td>1</td>\n",
243 |        "      <td>0</td>\n",
244 |        "    </tr>\n",
245 |        "    <tr>\n",
246 |        "      <th>4</th>\n",
247 |        "      <td>0</td>\n",
248 |        "      <td>1</td>\n",
249 |        "    </tr>\n",
250 |        "  </tbody>\n",
251 |        "</table>\n",
252 |        "</div>"
253 |       ],
254 |       "text/plain": [
255 |        "   Dummy_B  Dummy_C\n",
256 |        "0        0        0\n",
257 |        "1        1        0\n",
258 |        "2        0        0\n",
259 |        "3        1        0\n",
260 |        "4        0        1"
261 |       ]
262 |      },
263 |      "execution_count": 5,
264 |      "metadata": {},
265 |      "output_type": "execute_result"
266 |     }
267 |    ],
268 |    "source": [
269 |     "pd.get_dummies(dummies, prefix = \"Dummy\", drop_first = True)"
270 |    ]
271 |   },
272 |   {
273 |    "cell_type": "code",
274 |    "execution_count": null,
275 |    "id": "774a487b",
276 |    "metadata": {},
277 |    "outputs": [],
278 |    "source": []
279 |   }
280 |  ],
281 |  "metadata": {
282 |   "kernelspec": {
283 |    "display_name": "Python 3 (ipykernel)",
284 |    "language": "python",
285 |    "name": "python3"
286 |   },
287 |   "language_info": {
288 |    "codemirror_mode": {
289 |     "name": "ipython",
290 |     "version": 3
291 |    },
292 |    "file_extension": ".py",
293 |    "mimetype": "text/x-python",
294 |    "name": "python",
295 |    "nbconvert_exporter": "python",
296 |    "pygments_lexer": "ipython3",
297 |    "version": "3.9.13"
298 |   }
299 |  },
300 |  "nbformat": 4,
301 |  "nbformat_minor": 5
302 | }
303 | 


--------------------------------------------------------------------------------
/Session2/Quick_Web_Scraping_with_Pandas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "a00fe8f5",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "3a87ca23",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "verbs = pd.read_html(\"https://www.wse.com.tr/blog/irregular-verbs-duzensiz-fiiller/\")"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "markdown",
 25 |    "id": "4e0fae35",
 26 |    "metadata": {},
 27 |    "source": [
 28 |     "    -Errors-\n",
 29 |     "ImportError: html5lib not found, please install it\n",
 30 |     "pip install html5lib\n",
 31 |     "\n",
 32 |     "ValueError: No tables found\n",
 33 |     "\n",
 34 |     "urllib.error.HTTPError: HTTP Error 403: Forbidden"
 35 |    ]
 36 |   },
 37 |   {
 38 |    "cell_type": "markdown",
 39 |    "id": "ba595fe5",
 40 |    "metadata": {},
 41 |    "source": [
 42 |     "!pip install html5lib"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": 3,
 48 |    "id": "ed61c3f9",
 49 |    "metadata": {},
 50 |    "outputs": [
 51 |     {
 52 |      "data": {
 53 |       "text/html": [
 54 |        "<div>\n",
 55 |        "<style scoped>\n",
 56 |        "    .dataframe tbody tr th:only-of-type {\n",
 57 |        "        vertical-align: middle;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe tbody tr th {\n",
 61 |        "        vertical-align: top;\n",
 62 |        "    }\n",
 63 |        "\n",
 64 |        "    .dataframe thead th {\n",
 65 |        "        text-align: right;\n",
 66 |        "    }\n",
 67 |        "</style>\n",
 68 |        "<table border=\"1\" class=\"dataframe\">\n",
 69 |        "  <thead>\n",
 70 |        "    <tr style=\"text-align: right;\">\n",
 71 |        "      <th></th>\n",
 72 |        "      <th>0</th>\n",
 73 |        "      <th>1</th>\n",
 74 |        "      <th>2</th>\n",
 75 |        "      <th>3</th>\n",
 76 |        "    </tr>\n",
 77 |        "  </thead>\n",
 78 |        "  <tbody>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>0</th>\n",
 81 |        "      <td>V1 – Base Form</td>\n",
 82 |        "      <td>V2 – Past Simple</td>\n",
 83 |        "      <td>V3 – Past Participle</td>\n",
 84 |        "      <td>Türkçe Anlamı</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>1</th>\n",
 88 |        "      <td>awake</td>\n",
 89 |        "      <td>awoke</td>\n",
 90 |        "      <td>awoken</td>\n",
 91 |        "      <td>uyandırmak</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>2</th>\n",
 95 |        "      <td>be</td>\n",
 96 |        "      <td>was, were</td>\n",
 97 |        "      <td>been</td>\n",
 98 |        "      <td>olmak</td>\n",
 99 |        "    </tr>\n",
100 |        "    <tr>\n",
101 |        "      <th>3</th>\n",
102 |        "      <td>beat</td>\n",
103 |        "      <td>beat</td>\n",
104 |        "      <td>beaten</td>\n",
105 |        "      <td>vurmak</td>\n",
106 |        "    </tr>\n",
107 |        "    <tr>\n",
108 |        "      <th>4</th>\n",
109 |        "      <td>become</td>\n",
110 |        "      <td>became</td>\n",
111 |        "      <td>become</td>\n",
112 |        "      <td>olmak</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>...</th>\n",
116 |        "      <td>...</td>\n",
117 |        "      <td>...</td>\n",
118 |        "      <td>...</td>\n",
119 |        "      <td>...</td>\n",
120 |        "    </tr>\n",
121 |        "    <tr>\n",
122 |        "      <th>93</th>\n",
123 |        "      <td>understand</td>\n",
124 |        "      <td>understood</td>\n",
125 |        "      <td>understood</td>\n",
126 |        "      <td>anlamak</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>94</th>\n",
130 |        "      <td>wake</td>\n",
131 |        "      <td>woke</td>\n",
132 |        "      <td>woken</td>\n",
133 |        "      <td>uyanmak</td>\n",
134 |        "    </tr>\n",
135 |        "    <tr>\n",
136 |        "      <th>95</th>\n",
137 |        "      <td>wear</td>\n",
138 |        "      <td>wore</td>\n",
139 |        "      <td>worn</td>\n",
140 |        "      <td>giymek</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>96</th>\n",
144 |        "      <td>win</td>\n",
145 |        "      <td>won</td>\n",
146 |        "      <td>won</td>\n",
147 |        "      <td>kazanmak</td>\n",
148 |        "    </tr>\n",
149 |        "    <tr>\n",
150 |        "      <th>97</th>\n",
151 |        "      <td>write</td>\n",
152 |        "      <td>wrote</td>\n",
153 |        "      <td>written</td>\n",
154 |        "      <td>yazmak</td>\n",
155 |        "    </tr>\n",
156 |        "  </tbody>\n",
157 |        "</table>\n",
158 |        "<p>98 rows × 4 columns</p>\n",
159 |        "</div>"
160 |       ],
161 |       "text/plain": [
162 |        "                 0                 1                     2              3\n",
163 |        "0   V1 – Base Form  V2 – Past Simple  V3 – Past Participle  Türkçe Anlamı\n",
164 |        "1            awake             awoke                awoken     uyandırmak\n",
165 |        "2               be         was, were                  been          olmak\n",
166 |        "3             beat              beat                beaten         vurmak\n",
167 |        "4           become            became                become          olmak\n",
168 |        "..             ...               ...                   ...            ...\n",
169 |        "93      understand        understood            understood        anlamak\n",
170 |        "94            wake              woke                 woken        uyanmak\n",
171 |        "95            wear              wore                  worn         giymek\n",
172 |        "96             win               won                   won       kazanmak\n",
173 |        "97           write             wrote               written         yazmak\n",
174 |        "\n",
175 |        "[98 rows x 4 columns]"
176 |       ]
177 |      },
178 |      "execution_count": 3,
179 |      "metadata": {},
180 |      "output_type": "execute_result"
181 |     }
182 |    ],
183 |    "source": [
184 |     "verbs[0]"
185 |    ]
186 |   }
187 |  ],
188 |  "metadata": {
189 |   "kernelspec": {
190 |    "display_name": "Python 3 (ipykernel)",
191 |    "language": "python",
192 |    "name": "python3"
193 |   },
194 |   "language_info": {
195 |    "codemirror_mode": {
196 |     "name": "ipython",
197 |     "version": 3
198 |    },
199 |    "file_extension": ".py",
200 |    "mimetype": "text/x-python",
201 |    "name": "python",
202 |    "nbconvert_exporter": "python",
203 |    "pygments_lexer": "ipython3",
204 |    "version": "3.9.13"
205 |   }
206 |  },
207 |  "nbformat": 4,
208 |  "nbformat_minor": 5
209 | }
210 | 


--------------------------------------------------------------------------------
/Session2/create others values in pandas column.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "75e11a3a",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/plain": [
 12 |        "A        5\n",
 13 |        "Other    4\n",
 14 |        "B        2\n",
 15 |        "Name: genre, dtype: int64"
 16 |       ]
 17 |      },
 18 |      "execution_count": 1,
 19 |      "metadata": {},
 20 |      "output_type": "execute_result"
 21 |     }
 22 |    ],
 23 |    "source": [
 24 |     "import pandas as pd\n",
 25 |     "\n",
 26 |     "d = {\"genre\": [\"A\", \"A\", \"A\", \"A\", \"A\", \"B\", \"B\", \"C\", \"D\", \"E\", \"F\"]}\n",
 27 |     "df = pd.DataFrame(d)\n",
 28 |     "df[\"genre\"].value_counts()\n",
 29 |     "\n",
 30 |     "\n",
 31 |     "liste = ['A','B']\n",
 32 |     "\n",
 33 |     "# Step 2: update the df\n",
 34 |     "df_updated = df.where(df[\"genre\"].isin(liste), other = \"Other\")\n",
 35 |     "df_updated[\"genre\"].value_counts()"
 36 |    ]
 37 |   },
 38 |   {
 39 |    "cell_type": "code",
 40 |    "execution_count": 2,
 41 |    "id": "f65c3a91",
 42 |    "metadata": {},
 43 |    "outputs": [
 44 |     {
 45 |      "data": {
 46 |       "text/html": [
 47 |        "<div>\n",
 48 |        "<style scoped>\n",
 49 |        "    .dataframe tbody tr th:only-of-type {\n",
 50 |        "        vertical-align: middle;\n",
 51 |        "    }\n",
 52 |        "\n",
 53 |        "    .dataframe tbody tr th {\n",
 54 |        "        vertical-align: top;\n",
 55 |        "    }\n",
 56 |        "\n",
 57 |        "    .dataframe thead th {\n",
 58 |        "        text-align: right;\n",
 59 |        "    }\n",
 60 |        "</style>\n",
 61 |        "<table border=\"1\" class=\"dataframe\">\n",
 62 |        "  <thead>\n",
 63 |        "    <tr style=\"text-align: right;\">\n",
 64 |        "      <th></th>\n",
 65 |        "      <th>genre</th>\n",
 66 |        "    </tr>\n",
 67 |        "  </thead>\n",
 68 |        "  <tbody>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>0</th>\n",
 71 |        "      <td>A</td>\n",
 72 |        "    </tr>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>1</th>\n",
 75 |        "      <td>A</td>\n",
 76 |        "    </tr>\n",
 77 |        "    <tr>\n",
 78 |        "      <th>2</th>\n",
 79 |        "      <td>A</td>\n",
 80 |        "    </tr>\n",
 81 |        "    <tr>\n",
 82 |        "      <th>3</th>\n",
 83 |        "      <td>A</td>\n",
 84 |        "    </tr>\n",
 85 |        "    <tr>\n",
 86 |        "      <th>4</th>\n",
 87 |        "      <td>A</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>5</th>\n",
 91 |        "      <td>B</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>6</th>\n",
 95 |        "      <td>B</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>7</th>\n",
 99 |        "      <td>Other</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>8</th>\n",
103 |        "      <td>Other</td>\n",
104 |        "    </tr>\n",
105 |        "    <tr>\n",
106 |        "      <th>9</th>\n",
107 |        "      <td>Other</td>\n",
108 |        "    </tr>\n",
109 |        "    <tr>\n",
110 |        "      <th>10</th>\n",
111 |        "      <td>Other</td>\n",
112 |        "    </tr>\n",
113 |        "  </tbody>\n",
114 |        "</table>\n",
115 |        "</div>"
116 |       ],
117 |       "text/plain": [
118 |        "    genre\n",
119 |        "0       A\n",
120 |        "1       A\n",
121 |        "2       A\n",
122 |        "3       A\n",
123 |        "4       A\n",
124 |        "5       B\n",
125 |        "6       B\n",
126 |        "7   Other\n",
127 |        "8   Other\n",
128 |        "9   Other\n",
129 |        "10  Other"
130 |       ]
131 |      },
132 |      "execution_count": 2,
133 |      "metadata": {},
134 |      "output_type": "execute_result"
135 |     }
136 |    ],
137 |    "source": [
138 |     "df_updated"
139 |    ]
140 |   },
141 |   {
142 |    "cell_type": "code",
143 |    "execution_count": null,
144 |    "id": "b6a35980",
145 |    "metadata": {},
146 |    "outputs": [],
147 |    "source": []
148 |   }
149 |  ],
150 |  "metadata": {
151 |   "kernelspec": {
152 |    "display_name": "Python 3 (ipykernel)",
153 |    "language": "python",
154 |    "name": "python3"
155 |   },
156 |   "language_info": {
157 |    "codemirror_mode": {
158 |     "name": "ipython",
159 |     "version": 3
160 |    },
161 |    "file_extension": ".py",
162 |    "mimetype": "text/x-python",
163 |    "name": "python",
164 |    "nbconvert_exporter": "python",
165 |    "pygments_lexer": "ipython3",
166 |    "version": "3.9.13"
167 |   }
168 |  },
169 |  "nbformat": 4,
170 |  "nbformat_minor": 5
171 | }
172 | 


--------------------------------------------------------------------------------
/Session2/map function and assign numbers to category (factorize) and boolean.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "5889ac14",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>gender</th>\n",
 31 |        "      <th>color</th>\n",
 32 |        "      <th>age</th>\n",
 33 |        "      <th>gender_mapped</th>\n",
 34 |        "      <th>color_factorized</th>\n",
 35 |        "      <th>age_compared_boolean</th>\n",
 36 |        "    </tr>\n",
 37 |        "  </thead>\n",
 38 |        "  <tbody>\n",
 39 |        "    <tr>\n",
 40 |        "      <th>0</th>\n",
 41 |        "      <td>male</td>\n",
 42 |        "      <td>red</td>\n",
 43 |        "      <td>25</td>\n",
 44 |        "      <td>M</td>\n",
 45 |        "      <td>0</td>\n",
 46 |        "      <td>False</td>\n",
 47 |        "    </tr>\n",
 48 |        "    <tr>\n",
 49 |        "      <th>1</th>\n",
 50 |        "      <td>female</td>\n",
 51 |        "      <td>green</td>\n",
 52 |        "      <td>30</td>\n",
 53 |        "      <td>F</td>\n",
 54 |        "      <td>1</td>\n",
 55 |        "      <td>False</td>\n",
 56 |        "    </tr>\n",
 57 |        "    <tr>\n",
 58 |        "      <th>2</th>\n",
 59 |        "      <td>male</td>\n",
 60 |        "      <td>blue</td>\n",
 61 |        "      <td>15</td>\n",
 62 |        "      <td>M</td>\n",
 63 |        "      <td>2</td>\n",
 64 |        "      <td>True</td>\n",
 65 |        "    </tr>\n",
 66 |        "  </tbody>\n",
 67 |        "</table>\n",
 68 |        "</div>"
 69 |       ],
 70 |       "text/plain": [
 71 |        "   gender  color  age gender_mapped  color_factorized  age_compared_boolean\n",
 72 |        "0    male    red   25             M                 0                 False\n",
 73 |        "1  female  green   30             F                 1                 False\n",
 74 |        "2    male   blue   15             M                 2                  True"
 75 |       ]
 76 |      },
 77 |      "execution_count": 2,
 78 |      "metadata": {},
 79 |      "output_type": "execute_result"
 80 |     }
 81 |    ],
 82 |    "source": [
 83 |     "import pandas as pd\n",
 84 |     "# Do some fast feature eng on the DF\n",
 85 |     "d = {\"gender\":[\"male\", \"female\", \"male\"], \"color\":[\"red\", \"green\", \"blue\"], \"age\":[25, 30, 15]}\n",
 86 |     "df = pd.DataFrame(d)\n",
 87 |     "df\n",
 88 |     "\n",
 89 |     "# Solution\n",
 90 |     "map_dict = {\"male\":\"M\", \"female\":\"F\"}\n",
 91 |     "df[\"gender_mapped\"] = df[\"gender\"].map(map_dict) # using dictionaries to map values\n",
 92 |     "\n",
 93 |     "df[\"color_factorized\"] = df[\"color\"].factorize()[0] # using factorize: returns a tuple of arrays (array([0, 1, 2]), Index(['red', 'green', 'blue'], dtype='object')) that's why we select [0]\n",
 94 |     "\n",
 95 |     "df[\"age_compared_boolean\"] = df[\"age\"] < 18 # return a True False boolean value\n",
 96 |     "\n",
 97 |     "df"
 98 |    ]
 99 |   },
100 |   {
101 |    "cell_type": "code",
102 |    "execution_count": null,
103 |    "id": "cdeb5327",
104 |    "metadata": {},
105 |    "outputs": [],
106 |    "source": []
107 |   }
108 |  ],
109 |  "metadata": {
110 |   "kernelspec": {
111 |    "display_name": "Python 3 (ipykernel)",
112 |    "language": "python",
113 |    "name": "python3"
114 |   },
115 |   "language_info": {
116 |    "codemirror_mode": {
117 |     "name": "ipython",
118 |     "version": 3
119 |    },
120 |    "file_extension": ".py",
121 |    "mimetype": "text/x-python",
122 |    "name": "python",
123 |    "nbconvert_exporter": "python",
124 |    "pygments_lexer": "ipython3",
125 |    "version": "3.9.13"
126 |   }
127 |  },
128 |  "nbformat": 4,
129 |  "nbformat_minor": 5
130 | }
131 | 


--------------------------------------------------------------------------------
/Session2/select columns by slicing pandas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "cf777aaa",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": null,
 16 |    "id": "a6f12180",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "\tA\tB\tC\tD\tE\tF\tG\n",
 21 |     "0\t14\t16\t14\t2\t4\t11\t16\n",
 22 |     "1\t9\t14\t18\t18\t7\t5\t16\n",
 23 |     "2\t8\t18\t3\t19\t13\t18\t17\n",
 24 |     "3\t13\t13\t12\t4\t12\t1\t10\n",
 25 |     "4\t2\t7\t5\t2\t7\t2\t10\n",
 26 |     "5\t16\t5\t10\t3\t13\t16\t15\n",
 27 |     "6\t10\t13\t17\t9\t16\t12\t9\n",
 28 |     "7\t9\t16\t6\t19\t2\t11\t13\n",
 29 |     "8\t2\t3\t13\t13\t7\t14\t5\n",
 30 |     "9\t17\t8\t10\t18\t17\t8\t4\n",
 31 |     "10\t19\t14\t15\t1\t7\t8\t19\n",
 32 |     "11\t12\t16\t8\t19\t4\t4\t19\n",
 33 |     "12\t6\t1\t4\t9\t1\t5\t7\n",
 34 |     "13\t13\t13\t2\t12\t5\t10\t4\n",
 35 |     "14\t13\t5\t17\t1\t14\t19\t12\n",
 36 |     "15\t8\t18\t5\t8\t9\t15\t7\n",
 37 |     "16\t2\t1\t13\t12\t14\t12\t13\n",
 38 |     "17\t8\t6\t12\t18\t18\t1\t11"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 3,
 44 |    "id": "14e51ec1",
 45 |    "metadata": {},
 46 |    "outputs": [
 47 |     {
 48 |      "data": {
 49 |       "text/html": [
 50 |        "<div>\n",
 51 |        "<style scoped>\n",
 52 |        "    .dataframe tbody tr th:only-of-type {\n",
 53 |        "        vertical-align: middle;\n",
 54 |        "    }\n",
 55 |        "\n",
 56 |        "    .dataframe tbody tr th {\n",
 57 |        "        vertical-align: top;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe thead th {\n",
 61 |        "        text-align: right;\n",
 62 |        "    }\n",
 63 |        "</style>\n",
 64 |        "<table border=\"1\" class=\"dataframe\">\n",
 65 |        "  <thead>\n",
 66 |        "    <tr style=\"text-align: right;\">\n",
 67 |        "      <th></th>\n",
 68 |        "      <th>0</th>\n",
 69 |        "      <th>1</th>\n",
 70 |        "      <th>2</th>\n",
 71 |        "      <th>6</th>\n",
 72 |        "      <th>7</th>\n",
 73 |        "      <th>8</th>\n",
 74 |        "      <th>9</th>\n",
 75 |        "      <th>10</th>\n",
 76 |        "      <th>16</th>\n",
 77 |        "    </tr>\n",
 78 |        "  </thead>\n",
 79 |        "  <tbody>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>A</th>\n",
 82 |        "      <td>14</td>\n",
 83 |        "      <td>9</td>\n",
 84 |        "      <td>8</td>\n",
 85 |        "      <td>10</td>\n",
 86 |        "      <td>9</td>\n",
 87 |        "      <td>2</td>\n",
 88 |        "      <td>17</td>\n",
 89 |        "      <td>19</td>\n",
 90 |        "      <td>2</td>\n",
 91 |        "    </tr>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>B</th>\n",
 94 |        "      <td>16</td>\n",
 95 |        "      <td>14</td>\n",
 96 |        "      <td>18</td>\n",
 97 |        "      <td>13</td>\n",
 98 |        "      <td>16</td>\n",
 99 |        "      <td>3</td>\n",
100 |        "      <td>8</td>\n",
101 |        "      <td>14</td>\n",
102 |        "      <td>1</td>\n",
103 |        "    </tr>\n",
104 |        "    <tr>\n",
105 |        "      <th>C</th>\n",
106 |        "      <td>14</td>\n",
107 |        "      <td>18</td>\n",
108 |        "      <td>3</td>\n",
109 |        "      <td>17</td>\n",
110 |        "      <td>6</td>\n",
111 |        "      <td>13</td>\n",
112 |        "      <td>10</td>\n",
113 |        "      <td>15</td>\n",
114 |        "      <td>13</td>\n",
115 |        "    </tr>\n",
116 |        "    <tr>\n",
117 |        "      <th>D</th>\n",
118 |        "      <td>2</td>\n",
119 |        "      <td>18</td>\n",
120 |        "      <td>19</td>\n",
121 |        "      <td>9</td>\n",
122 |        "      <td>19</td>\n",
123 |        "      <td>13</td>\n",
124 |        "      <td>18</td>\n",
125 |        "      <td>1</td>\n",
126 |        "      <td>12</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>E</th>\n",
130 |        "      <td>4</td>\n",
131 |        "      <td>7</td>\n",
132 |        "      <td>13</td>\n",
133 |        "      <td>16</td>\n",
134 |        "      <td>2</td>\n",
135 |        "      <td>7</td>\n",
136 |        "      <td>17</td>\n",
137 |        "      <td>7</td>\n",
138 |        "      <td>14</td>\n",
139 |        "    </tr>\n",
140 |        "    <tr>\n",
141 |        "      <th>F</th>\n",
142 |        "      <td>11</td>\n",
143 |        "      <td>5</td>\n",
144 |        "      <td>18</td>\n",
145 |        "      <td>12</td>\n",
146 |        "      <td>11</td>\n",
147 |        "      <td>14</td>\n",
148 |        "      <td>8</td>\n",
149 |        "      <td>8</td>\n",
150 |        "      <td>12</td>\n",
151 |        "    </tr>\n",
152 |        "    <tr>\n",
153 |        "      <th>G</th>\n",
154 |        "      <td>16</td>\n",
155 |        "      <td>16</td>\n",
156 |        "      <td>17</td>\n",
157 |        "      <td>9</td>\n",
158 |        "      <td>13</td>\n",
159 |        "      <td>5</td>\n",
160 |        "      <td>4</td>\n",
161 |        "      <td>19</td>\n",
162 |        "      <td>13</td>\n",
163 |        "    </tr>\n",
164 |        "  </tbody>\n",
165 |        "</table>\n",
166 |        "</div>"
167 |       ],
168 |       "text/plain": [
169 |        "    0   1   2   6   7   8   9  10  16\n",
170 |        "A  14   9   8  10   9   2  17  19   2\n",
171 |        "B  16  14  18  13  16   3   8  14   1\n",
172 |        "C  14  18   3  17   6  13  10  15  13\n",
173 |        "D   2  18  19   9  19  13  18   1  12\n",
174 |        "E   4   7  13  16   2   7  17   7  14\n",
175 |        "F  11   5  18  12  11  14   8   8  12\n",
176 |        "G  16  16  17   9  13   5   4  19  13"
177 |       ]
178 |      },
179 |      "execution_count": 3,
180 |      "metadata": {},
181 |      "output_type": "execute_result"
182 |     }
183 |    ],
184 |    "source": [
185 |     "df = pd.read_clipboard()\n",
186 |     "\n",
187 |     "import numpy as np\n",
188 |     "df = df.T\n",
189 |     "cols_str = list(map(str, list(df.columns))) # so that we can do df[\"0\"] as string for the example\n",
190 |     "df.columns = cols_str\n",
191 |     "\n",
192 |     "# Using pandas concatenation\n",
193 |     "# if you are ever confused about axis = 1 or axis = 0, just put axis = \"columns\" or axis = \"rows\"\n",
194 |     "pd.concat([df.loc[:, \"0\":\"2\"], df.loc[:, \"6\":\"10\"], df.loc[:, \"16\":\"17\"]], axis = \"columns\") # ------------------> here we are selecting columns converted to strings\n",
195 |     "\n",
196 |     "# Using lists\n",
197 |     "# please ntoe that df.columns is a series with index, so we are using index to filter # -------------------------> here we are selecting the index of columns\n",
198 |     "df[list(df.columns[0:3]) + list(df.columns[6:11]) + list(df.columns[16:17])]\n",
199 |     "\n",
200 |     "# Using numpy\n",
201 |     "df.iloc[:, np.r_[0:3, 6:11, 16:17]] # probably the most beautiful solution"
202 |    ]
203 |   },
204 |   {
205 |    "cell_type": "code",
206 |    "execution_count": 4,
207 |    "id": "263bcf86",
208 |    "metadata": {},
209 |    "outputs": [
210 |     {
211 |      "data": {
212 |       "text/plain": [
213 |        "array([ 0,  1,  2,  6,  7,  8,  9, 10, 16])"
214 |       ]
215 |      },
216 |      "execution_count": 4,
217 |      "metadata": {},
218 |      "output_type": "execute_result"
219 |     }
220 |    ],
221 |    "source": [
222 |     "np.r_[0:3, 6:11, 16:17]"
223 |    ]
224 |   },
225 |   {
226 |    "cell_type": "code",
227 |    "execution_count": null,
228 |    "id": "4af6b356",
229 |    "metadata": {},
230 |    "outputs": [],
231 |    "source": []
232 |   }
233 |  ],
234 |  "metadata": {
235 |   "kernelspec": {
236 |    "display_name": "Python 3 (ipykernel)",
237 |    "language": "python",
238 |    "name": "python3"
239 |   },
240 |   "language_info": {
241 |    "codemirror_mode": {
242 |     "name": "ipython",
243 |     "version": 3
244 |    },
245 |    "file_extension": ".py",
246 |    "mimetype": "text/x-python",
247 |    "name": "python",
248 |    "nbconvert_exporter": "python",
249 |    "pygments_lexer": "ipython3",
250 |    "version": "3.9.13"
251 |   }
252 |  },
253 |  "nbformat": 4,
254 |  "nbformat_minor": 5
255 | }
256 | 


--------------------------------------------------------------------------------
/Session3/Deal_with_zip_files.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "provenance": []
  7 |     },
  8 |     "kernelspec": {
  9 |       "name": "python3",
 10 |       "display_name": "Python 3"
 11 |     },
 12 |     "language_info": {
 13 |       "name": "python"
 14 |     }
 15 |   },
 16 |   "cells": [
 17 |     {
 18 |       "cell_type": "code",
 19 |       "execution_count": 20,
 20 |       "metadata": {
 21 |         "colab": {
 22 |           "base_uri": "https://localhost:8080/",
 23 |           "height": 848
 24 |         },
 25 |         "id": "KoG7NgjdhDR3",
 26 |         "outputId": "b3d2fe98-01aa-47c5-a8e8-7bbf388b5eac"
 27 |       },
 28 |       "outputs": [
 29 |         {
 30 |           "output_type": "display_data",
 31 |           "data": {
 32 |             "text/plain": [
 33 |               "        v1                                                 v2 Unnamed: 2  \\\n",
 34 |               "0      ham  Go until jurong point, crazy.. Available only ...        NaN   \n",
 35 |               "1      ham                      Ok lar... Joking wif u oni...        NaN   \n",
 36 |               "2     spam  Free entry in 2 a wkly comp to win FA Cup fina...        NaN   \n",
 37 |               "3      ham  U dun say so early hor... U c already then say...        NaN   \n",
 38 |               "4      ham  Nah I don't think he goes to usf, he lives aro...        NaN   \n",
 39 |               "...    ...                                                ...        ...   \n",
 40 |               "5567  spam  This is the 2nd time we have tried 2 contact u...        NaN   \n",
 41 |               "5568   ham              Will Ì_ b going to esplanade fr home?        NaN   \n",
 42 |               "5569   ham  Pity, * was in mood for that. So...any other s...        NaN   \n",
 43 |               "5570   ham  The guy did some bitching but I acted like i'd...        NaN   \n",
 44 |               "5571   ham                         Rofl. Its true to its name        NaN   \n",
 45 |               "\n",
 46 |               "     Unnamed: 3 Unnamed: 4  \n",
 47 |               "0           NaN        NaN  \n",
 48 |               "1           NaN        NaN  \n",
 49 |               "2           NaN        NaN  \n",
 50 |               "3           NaN        NaN  \n",
 51 |               "4           NaN        NaN  \n",
 52 |               "...         ...        ...  \n",
 53 |               "5567        NaN        NaN  \n",
 54 |               "5568        NaN        NaN  \n",
 55 |               "5569        NaN        NaN  \n",
 56 |               "5570        NaN        NaN  \n",
 57 |               "5571        NaN        NaN  \n",
 58 |               "\n",
 59 |               "[5572 rows x 5 columns]"
 60 |             ],
 61 |             "text/html": [
 62 |               "\n",
 63 |               "  <div id=\"df-4cd69c1c-f629-4b72-bf20-0fe5c032975e\">\n",
 64 |               "    <div class=\"colab-df-container\">\n",
 65 |               "      <div>\n",
 66 |               "<style scoped>\n",
 67 |               "    .dataframe tbody tr th:only-of-type {\n",
 68 |               "        vertical-align: middle;\n",
 69 |               "    }\n",
 70 |               "\n",
 71 |               "    .dataframe tbody tr th {\n",
 72 |               "        vertical-align: top;\n",
 73 |               "    }\n",
 74 |               "\n",
 75 |               "    .dataframe thead th {\n",
 76 |               "        text-align: right;\n",
 77 |               "    }\n",
 78 |               "</style>\n",
 79 |               "<table border=\"1\" class=\"dataframe\">\n",
 80 |               "  <thead>\n",
 81 |               "    <tr style=\"text-align: right;\">\n",
 82 |               "      <th></th>\n",
 83 |               "      <th>v1</th>\n",
 84 |               "      <th>v2</th>\n",
 85 |               "      <th>Unnamed: 2</th>\n",
 86 |               "      <th>Unnamed: 3</th>\n",
 87 |               "      <th>Unnamed: 4</th>\n",
 88 |               "    </tr>\n",
 89 |               "  </thead>\n",
 90 |               "  <tbody>\n",
 91 |               "    <tr>\n",
 92 |               "      <th>0</th>\n",
 93 |               "      <td>ham</td>\n",
 94 |               "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
 95 |               "      <td>NaN</td>\n",
 96 |               "      <td>NaN</td>\n",
 97 |               "      <td>NaN</td>\n",
 98 |               "    </tr>\n",
 99 |               "    <tr>\n",
100 |               "      <th>1</th>\n",
101 |               "      <td>ham</td>\n",
102 |               "      <td>Ok lar... Joking wif u oni...</td>\n",
103 |               "      <td>NaN</td>\n",
104 |               "      <td>NaN</td>\n",
105 |               "      <td>NaN</td>\n",
106 |               "    </tr>\n",
107 |               "    <tr>\n",
108 |               "      <th>2</th>\n",
109 |               "      <td>spam</td>\n",
110 |               "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
111 |               "      <td>NaN</td>\n",
112 |               "      <td>NaN</td>\n",
113 |               "      <td>NaN</td>\n",
114 |               "    </tr>\n",
115 |               "    <tr>\n",
116 |               "      <th>3</th>\n",
117 |               "      <td>ham</td>\n",
118 |               "      <td>U dun say so early hor... U c already then say...</td>\n",
119 |               "      <td>NaN</td>\n",
120 |               "      <td>NaN</td>\n",
121 |               "      <td>NaN</td>\n",
122 |               "    </tr>\n",
123 |               "    <tr>\n",
124 |               "      <th>4</th>\n",
125 |               "      <td>ham</td>\n",
126 |               "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
127 |               "      <td>NaN</td>\n",
128 |               "      <td>NaN</td>\n",
129 |               "      <td>NaN</td>\n",
130 |               "    </tr>\n",
131 |               "    <tr>\n",
132 |               "      <th>...</th>\n",
133 |               "      <td>...</td>\n",
134 |               "      <td>...</td>\n",
135 |               "      <td>...</td>\n",
136 |               "      <td>...</td>\n",
137 |               "      <td>...</td>\n",
138 |               "    </tr>\n",
139 |               "    <tr>\n",
140 |               "      <th>5567</th>\n",
141 |               "      <td>spam</td>\n",
142 |               "      <td>This is the 2nd time we have tried 2 contact u...</td>\n",
143 |               "      <td>NaN</td>\n",
144 |               "      <td>NaN</td>\n",
145 |               "      <td>NaN</td>\n",
146 |               "    </tr>\n",
147 |               "    <tr>\n",
148 |               "      <th>5568</th>\n",
149 |               "      <td>ham</td>\n",
150 |               "      <td>Will Ì_ b going to esplanade fr home?</td>\n",
151 |               "      <td>NaN</td>\n",
152 |               "      <td>NaN</td>\n",
153 |               "      <td>NaN</td>\n",
154 |               "    </tr>\n",
155 |               "    <tr>\n",
156 |               "      <th>5569</th>\n",
157 |               "      <td>ham</td>\n",
158 |               "      <td>Pity, * was in mood for that. So...any other s...</td>\n",
159 |               "      <td>NaN</td>\n",
160 |               "      <td>NaN</td>\n",
161 |               "      <td>NaN</td>\n",
162 |               "    </tr>\n",
163 |               "    <tr>\n",
164 |               "      <th>5570</th>\n",
165 |               "      <td>ham</td>\n",
166 |               "      <td>The guy did some bitching but I acted like i'd...</td>\n",
167 |               "      <td>NaN</td>\n",
168 |               "      <td>NaN</td>\n",
169 |               "      <td>NaN</td>\n",
170 |               "    </tr>\n",
171 |               "    <tr>\n",
172 |               "      <th>5571</th>\n",
173 |               "      <td>ham</td>\n",
174 |               "      <td>Rofl. Its true to its name</td>\n",
175 |               "      <td>NaN</td>\n",
176 |               "      <td>NaN</td>\n",
177 |               "      <td>NaN</td>\n",
178 |               "    </tr>\n",
179 |               "  </tbody>\n",
180 |               "</table>\n",
181 |               "<p>5572 rows × 5 columns</p>\n",
182 |               "</div>\n",
183 |               "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4cd69c1c-f629-4b72-bf20-0fe5c032975e')\"\n",
184 |               "              title=\"Convert this dataframe to an interactive table.\"\n",
185 |               "              style=\"display:none;\">\n",
186 |               "        \n",
187 |               "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
188 |               "       width=\"24px\">\n",
189 |               "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
190 |               "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
191 |               "  </svg>\n",
192 |               "      </button>\n",
193 |               "      \n",
194 |               "  <style>\n",
195 |               "    .colab-df-container {\n",
196 |               "      display:flex;\n",
197 |               "      flex-wrap:wrap;\n",
198 |               "      gap: 12px;\n",
199 |               "    }\n",
200 |               "\n",
201 |               "    .colab-df-convert {\n",
202 |               "      background-color: #E8F0FE;\n",
203 |               "      border: none;\n",
204 |               "      border-radius: 50%;\n",
205 |               "      cursor: pointer;\n",
206 |               "      display: none;\n",
207 |               "      fill: #1967D2;\n",
208 |               "      height: 32px;\n",
209 |               "      padding: 0 0 0 0;\n",
210 |               "      width: 32px;\n",
211 |               "    }\n",
212 |               "\n",
213 |               "    .colab-df-convert:hover {\n",
214 |               "      background-color: #E2EBFA;\n",
215 |               "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
216 |               "      fill: #174EA6;\n",
217 |               "    }\n",
218 |               "\n",
219 |               "    [theme=dark] .colab-df-convert {\n",
220 |               "      background-color: #3B4455;\n",
221 |               "      fill: #D2E3FC;\n",
222 |               "    }\n",
223 |               "\n",
224 |               "    [theme=dark] .colab-df-convert:hover {\n",
225 |               "      background-color: #434B5C;\n",
226 |               "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
227 |               "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
228 |               "      fill: #FFFFFF;\n",
229 |               "    }\n",
230 |               "  </style>\n",
231 |               "\n",
232 |               "      <script>\n",
233 |               "        const buttonEl =\n",
234 |               "          document.querySelector('#df-4cd69c1c-f629-4b72-bf20-0fe5c032975e button.colab-df-convert');\n",
235 |               "        buttonEl.style.display =\n",
236 |               "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
237 |               "\n",
238 |               "        async function convertToInteractive(key) {\n",
239 |               "          const element = document.querySelector('#df-4cd69c1c-f629-4b72-bf20-0fe5c032975e');\n",
240 |               "          const dataTable =\n",
241 |               "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
242 |               "                                                     [key], {});\n",
243 |               "          if (!dataTable) return;\n",
244 |               "\n",
245 |               "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
246 |               "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
247 |               "            + ' to learn more about interactive tables.';\n",
248 |               "          element.innerHTML = '';\n",
249 |               "          dataTable['output_type'] = 'display_data';\n",
250 |               "          await google.colab.output.renderOutput(dataTable, element);\n",
251 |               "          const docLink = document.createElement('div');\n",
252 |               "          docLink.innerHTML = docLinkHtml;\n",
253 |               "          element.appendChild(docLink);\n",
254 |               "        }\n",
255 |               "      </script>\n",
256 |               "    </div>\n",
257 |               "  </div>\n",
258 |               "  "
259 |             ]
260 |           },
261 |           "metadata": {}
262 |         },
263 |         {
264 |           "output_type": "stream",
265 |           "name": "stdout",
266 |           "text": [
267 |             "Compressing ratio(perc):  43.10390383083717\n"
268 |           ]
269 |         },
270 |         {
271 |           "output_type": "display_data",
272 |           "data": {
273 |             "text/plain": [
274 |               "      Unnamed: 0    v1                                                 v2  \\\n",
275 |               "0              0   ham  Go until jurong point, crazy.. Available only ...   \n",
276 |               "1              1   ham                      Ok lar... Joking wif u oni...   \n",
277 |               "2              2  spam  Free entry in 2 a wkly comp to win FA Cup fina...   \n",
278 |               "3              3   ham  U dun say so early hor... U c already then say...   \n",
279 |               "4              4   ham  Nah I don't think he goes to usf, he lives aro...   \n",
280 |               "...          ...   ...                                                ...   \n",
281 |               "5567        5567  spam  This is the 2nd time we have tried 2 contact u...   \n",
282 |               "5568        5568   ham              Will Ì_ b going to esplanade fr home?   \n",
283 |               "5569        5569   ham  Pity, * was in mood for that. So...any other s...   \n",
284 |               "5570        5570   ham  The guy did some bitching but I acted like i'd...   \n",
285 |               "5571        5571   ham                         Rofl. Its true to its name   \n",
286 |               "\n",
287 |               "     Unnamed: 2 Unnamed: 3 Unnamed: 4  \n",
288 |               "0           NaN        NaN        NaN  \n",
289 |               "1           NaN        NaN        NaN  \n",
290 |               "2           NaN        NaN        NaN  \n",
291 |               "3           NaN        NaN        NaN  \n",
292 |               "4           NaN        NaN        NaN  \n",
293 |               "...         ...        ...        ...  \n",
294 |               "5567        NaN        NaN        NaN  \n",
295 |               "5568        NaN        NaN        NaN  \n",
296 |               "5569        NaN        NaN        NaN  \n",
297 |               "5570        NaN        NaN        NaN  \n",
298 |               "5571        NaN        NaN        NaN  \n",
299 |               "\n",
300 |               "[5572 rows x 6 columns]"
301 |             ],
302 |             "text/html": [
303 |               "\n",
304 |               "  <div id=\"df-37835453-b997-44ac-a268-2e94e4adb163\">\n",
305 |               "    <div class=\"colab-df-container\">\n",
306 |               "      <div>\n",
307 |               "<style scoped>\n",
308 |               "    .dataframe tbody tr th:only-of-type {\n",
309 |               "        vertical-align: middle;\n",
310 |               "    }\n",
311 |               "\n",
312 |               "    .dataframe tbody tr th {\n",
313 |               "        vertical-align: top;\n",
314 |               "    }\n",
315 |               "\n",
316 |               "    .dataframe thead th {\n",
317 |               "        text-align: right;\n",
318 |               "    }\n",
319 |               "</style>\n",
320 |               "<table border=\"1\" class=\"dataframe\">\n",
321 |               "  <thead>\n",
322 |               "    <tr style=\"text-align: right;\">\n",
323 |               "      <th></th>\n",
324 |               "      <th>Unnamed: 0</th>\n",
325 |               "      <th>v1</th>\n",
326 |               "      <th>v2</th>\n",
327 |               "      <th>Unnamed: 2</th>\n",
328 |               "      <th>Unnamed: 3</th>\n",
329 |               "      <th>Unnamed: 4</th>\n",
330 |               "    </tr>\n",
331 |               "  </thead>\n",
332 |               "  <tbody>\n",
333 |               "    <tr>\n",
334 |               "      <th>0</th>\n",
335 |               "      <td>0</td>\n",
336 |               "      <td>ham</td>\n",
337 |               "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
338 |               "      <td>NaN</td>\n",
339 |               "      <td>NaN</td>\n",
340 |               "      <td>NaN</td>\n",
341 |               "    </tr>\n",
342 |               "    <tr>\n",
343 |               "      <th>1</th>\n",
344 |               "      <td>1</td>\n",
345 |               "      <td>ham</td>\n",
346 |               "      <td>Ok lar... Joking wif u oni...</td>\n",
347 |               "      <td>NaN</td>\n",
348 |               "      <td>NaN</td>\n",
349 |               "      <td>NaN</td>\n",
350 |               "    </tr>\n",
351 |               "    <tr>\n",
352 |               "      <th>2</th>\n",
353 |               "      <td>2</td>\n",
354 |               "      <td>spam</td>\n",
355 |               "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
356 |               "      <td>NaN</td>\n",
357 |               "      <td>NaN</td>\n",
358 |               "      <td>NaN</td>\n",
359 |               "    </tr>\n",
360 |               "    <tr>\n",
361 |               "      <th>3</th>\n",
362 |               "      <td>3</td>\n",
363 |               "      <td>ham</td>\n",
364 |               "      <td>U dun say so early hor... U c already then say...</td>\n",
365 |               "      <td>NaN</td>\n",
366 |               "      <td>NaN</td>\n",
367 |               "      <td>NaN</td>\n",
368 |               "    </tr>\n",
369 |               "    <tr>\n",
370 |               "      <th>4</th>\n",
371 |               "      <td>4</td>\n",
372 |               "      <td>ham</td>\n",
373 |               "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
374 |               "      <td>NaN</td>\n",
375 |               "      <td>NaN</td>\n",
376 |               "      <td>NaN</td>\n",
377 |               "    </tr>\n",
378 |               "    <tr>\n",
379 |               "      <th>...</th>\n",
380 |               "      <td>...</td>\n",
381 |               "      <td>...</td>\n",
382 |               "      <td>...</td>\n",
383 |               "      <td>...</td>\n",
384 |               "      <td>...</td>\n",
385 |               "      <td>...</td>\n",
386 |               "    </tr>\n",
387 |               "    <tr>\n",
388 |               "      <th>5567</th>\n",
389 |               "      <td>5567</td>\n",
390 |               "      <td>spam</td>\n",
391 |               "      <td>This is the 2nd time we have tried 2 contact u...</td>\n",
392 |               "      <td>NaN</td>\n",
393 |               "      <td>NaN</td>\n",
394 |               "      <td>NaN</td>\n",
395 |               "    </tr>\n",
396 |               "    <tr>\n",
397 |               "      <th>5568</th>\n",
398 |               "      <td>5568</td>\n",
399 |               "      <td>ham</td>\n",
400 |               "      <td>Will Ì_ b going to esplanade fr home?</td>\n",
401 |               "      <td>NaN</td>\n",
402 |               "      <td>NaN</td>\n",
403 |               "      <td>NaN</td>\n",
404 |               "    </tr>\n",
405 |               "    <tr>\n",
406 |               "      <th>5569</th>\n",
407 |               "      <td>5569</td>\n",
408 |               "      <td>ham</td>\n",
409 |               "      <td>Pity, * was in mood for that. So...any other s...</td>\n",
410 |               "      <td>NaN</td>\n",
411 |               "      <td>NaN</td>\n",
412 |               "      <td>NaN</td>\n",
413 |               "    </tr>\n",
414 |               "    <tr>\n",
415 |               "      <th>5570</th>\n",
416 |               "      <td>5570</td>\n",
417 |               "      <td>ham</td>\n",
418 |               "      <td>The guy did some bitching but I acted like i'd...</td>\n",
419 |               "      <td>NaN</td>\n",
420 |               "      <td>NaN</td>\n",
421 |               "      <td>NaN</td>\n",
422 |               "    </tr>\n",
423 |               "    <tr>\n",
424 |               "      <th>5571</th>\n",
425 |               "      <td>5571</td>\n",
426 |               "      <td>ham</td>\n",
427 |               "      <td>Rofl. Its true to its name</td>\n",
428 |               "      <td>NaN</td>\n",
429 |               "      <td>NaN</td>\n",
430 |               "      <td>NaN</td>\n",
431 |               "    </tr>\n",
432 |               "  </tbody>\n",
433 |               "</table>\n",
434 |               "<p>5572 rows × 6 columns</p>\n",
435 |               "</div>\n",
436 |               "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-37835453-b997-44ac-a268-2e94e4adb163')\"\n",
437 |               "              title=\"Convert this dataframe to an interactive table.\"\n",
438 |               "              style=\"display:none;\">\n",
439 |               "        \n",
440 |               "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
441 |               "       width=\"24px\">\n",
442 |               "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
443 |               "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
444 |               "  </svg>\n",
445 |               "      </button>\n",
446 |               "      \n",
447 |               "  <style>\n",
448 |               "    .colab-df-container {\n",
449 |               "      display:flex;\n",
450 |               "      flex-wrap:wrap;\n",
451 |               "      gap: 12px;\n",
452 |               "    }\n",
453 |               "\n",
454 |               "    .colab-df-convert {\n",
455 |               "      background-color: #E8F0FE;\n",
456 |               "      border: none;\n",
457 |               "      border-radius: 50%;\n",
458 |               "      cursor: pointer;\n",
459 |               "      display: none;\n",
460 |               "      fill: #1967D2;\n",
461 |               "      height: 32px;\n",
462 |               "      padding: 0 0 0 0;\n",
463 |               "      width: 32px;\n",
464 |               "    }\n",
465 |               "\n",
466 |               "    .colab-df-convert:hover {\n",
467 |               "      background-color: #E2EBFA;\n",
468 |               "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
469 |               "      fill: #174EA6;\n",
470 |               "    }\n",
471 |               "\n",
472 |               "    [theme=dark] .colab-df-convert {\n",
473 |               "      background-color: #3B4455;\n",
474 |               "      fill: #D2E3FC;\n",
475 |               "    }\n",
476 |               "\n",
477 |               "    [theme=dark] .colab-df-convert:hover {\n",
478 |               "      background-color: #434B5C;\n",
479 |               "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
480 |               "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
481 |               "      fill: #FFFFFF;\n",
482 |               "    }\n",
483 |               "  </style>\n",
484 |               "\n",
485 |               "      <script>\n",
486 |               "        const buttonEl =\n",
487 |               "          document.querySelector('#df-37835453-b997-44ac-a268-2e94e4adb163 button.colab-df-convert');\n",
488 |               "        buttonEl.style.display =\n",
489 |               "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
490 |               "\n",
491 |               "        async function convertToInteractive(key) {\n",
492 |               "          const element = document.querySelector('#df-37835453-b997-44ac-a268-2e94e4adb163');\n",
493 |               "          const dataTable =\n",
494 |               "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
495 |               "                                                     [key], {});\n",
496 |               "          if (!dataTable) return;\n",
497 |               "\n",
498 |               "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
499 |               "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
500 |               "            + ' to learn more about interactive tables.';\n",
501 |               "          element.innerHTML = '';\n",
502 |               "          dataTable['output_type'] = 'display_data';\n",
503 |               "          await google.colab.output.renderOutput(dataTable, element);\n",
504 |               "          const docLink = document.createElement('div');\n",
505 |               "          docLink.innerHTML = docLinkHtml;\n",
506 |               "          element.appendChild(docLink);\n",
507 |               "        }\n",
508 |               "      </script>\n",
509 |               "    </div>\n",
510 |               "  </div>\n",
511 |               "  "
512 |             ]
513 |           },
514 |           "metadata": {}
515 |         }
516 |       ],
517 |       "source": [
518 |         "import pandas as pd\n",
519 |         "\n",
520 |         "\"\"\"\n",
521 |         "------------ WRITE ZIP FILES -----------\n",
522 |         "\"\"\"\n",
523 |         "# Read data from internet\n",
524 |         "url = \"https://raw.githubusercontent.com/keitazoumana/Fastapi-tutorial/master/data/spam.csv\"\n",
525 |         "spam_data = pd.read_csv(url, encoding=\"ISO-8859-1\")\n",
526 |         "display(spam_data)\n",
527 |         "# Save it as a .csv file\n",
528 |         "spam_data.to_csv(\"spam.csv\")\n",
529 |         "# Save it as a zip file\n",
530 |         "spam_data.to_csv(\"spam.csv.zip\", compression=\"zip\")\n",
531 |         "\n",
532 |         "# Check the files sizes\n",
533 |         "from os import path\n",
534 |         "print(\"Compressing ratio(perc): \", 100 * path.getsize('spam.csv.zip') /  path.getsize('spam.csv'))\n",
535 |         "\n",
536 |         "\n",
537 |         "\"\"\"\n",
538 |         "------------ READ ZIP FILES -----------\n",
539 |         "\"\"\"\n",
540 |         "# Case 1: read a single zip file \n",
541 |         "spam_df_unzip = pd.read_csv('spam.csv.zip', compression='zip')\n",
542 |         "\n",
543 |         "# Case 2: read a file from a folder\n",
544 |         "from zipfile import ZipFile\n",
545 |         "\n",
546 |         "# Read the file from a zip folder\n",
547 |         "spam_df = pd.read_csv(ZipFile(\"spam.csv.zip\").open('spam.csv'))\n",
548 |         "display(spam_df)"
549 |       ]
550 |     }
551 |   ]
552 | }


--------------------------------------------------------------------------------
/Session3/count words in row.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "332c8e4c",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>Title</th>\n",
 31 |        "      <th>Words</th>\n",
 32 |        "    </tr>\n",
 33 |        "  </thead>\n",
 34 |        "  <tbody>\n",
 35 |        "    <tr>\n",
 36 |        "      <th>0</th>\n",
 37 |        "      <td>allows us to input information when a image wi...</td>\n",
 38 |        "      <td>11</td>\n",
 39 |        "    </tr>\n",
 40 |        "    <tr>\n",
 41 |        "      <th>1</th>\n",
 42 |        "      <td>By leaving it blank it just waits for anykey t...</td>\n",
 43 |        "      <td>13</td>\n",
 44 |        "    </tr>\n",
 45 |        "    <tr>\n",
 46 |        "      <th>2</th>\n",
 47 |        "      <td>continuing. By placing numbers (except 0), we ...</td>\n",
 48 |        "      <td>12</td>\n",
 49 |        "    </tr>\n",
 50 |        "    <tr>\n",
 51 |        "      <th>3</th>\n",
 52 |        "      <td>how long you keep the window open (time is in ...</td>\n",
 53 |        "      <td>12</td>\n",
 54 |        "    </tr>\n",
 55 |        "  </tbody>\n",
 56 |        "</table>\n",
 57 |        "</div>"
 58 |       ],
 59 |       "text/plain": [
 60 |        "                                               Title  Words\n",
 61 |        "0  allows us to input information when a image wi...     11\n",
 62 |        "1  By leaving it blank it just waits for anykey t...     13\n",
 63 |        "2  continuing. By placing numbers (except 0), we ...     12\n",
 64 |        "3  how long you keep the window open (time is in ...     12"
 65 |       ]
 66 |      },
 67 |      "execution_count": 1,
 68 |      "metadata": {},
 69 |      "output_type": "execute_result"
 70 |     }
 71 |    ],
 72 |    "source": [
 73 |     "import pandas as pd\n",
 74 |     "df = pd.DataFrame({\"Title\":[\"allows us to input information when a image window is open\"\n",
 75 |     ",\"By leaving it blank it just waits for anykey to be pressed before\" \n",
 76 |     ",\"continuing. By placing numbers (except 0), we can specify a delay for\"\n",
 77 |     ",\"how long you keep the window open (time is in milliseconds here)\"]})\n",
 78 |     "\n",
 79 |     "df[\"Words\"] = df[\"Title\"].str.count(\" \") + 1\n",
 80 |     "df"
 81 |    ]
 82 |   },
 83 |   {
 84 |    "cell_type": "code",
 85 |    "execution_count": null,
 86 |    "id": "d3ecff59",
 87 |    "metadata": {},
 88 |    "outputs": [],
 89 |    "source": []
 90 |   }
 91 |  ],
 92 |  "metadata": {
 93 |   "kernelspec": {
 94 |    "display_name": "Python 3 (ipykernel)",
 95 |    "language": "python",
 96 |    "name": "python3"
 97 |   },
 98 |   "language_info": {
 99 |    "codemirror_mode": {
100 |     "name": "ipython",
101 |     "version": 3
102 |    },
103 |    "file_extension": ".py",
104 |    "mimetype": "text/x-python",
105 |    "name": "python",
106 |    "nbconvert_exporter": "python",
107 |    "pygments_lexer": "ipython3",
108 |    "version": "3.9.13"
109 |   }
110 |  },
111 |  "nbformat": 4,
112 |  "nbformat_minor": 5
113 | }
114 | 


--------------------------------------------------------------------------------
/Session3/pd.cut pd.qcut.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 59,
  6 |    "id": "81772eea",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "\n",
 11 |     "import random\n",
 12 |     "\n",
 13 |     "# np.random.randint(low = 3,high=8,size=10)\n",
 14 |     "df = pd.DataFrame({\"nums\":random.sample(range(1, 100), 15)})"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 60,
 20 |    "id": "873a4bad",
 21 |    "metadata": {},
 22 |    "outputs": [],
 23 |    "source": [
 24 |     "df[\"bin\"] = pd.cut(df[\"nums\"], bins = [0, 15, 50, 80, 99])\n",
 25 |     "\n",
 26 |     "df[\"bin_cat\"] = pd.cut(df[\"nums\"], bins = [0, 15, 50, 80, 99],labels = [\"awful\", \"bad\", \"average\", \"good\"])"
 27 |    ]
 28 |   },
 29 |   {
 30 |    "cell_type": "code",
 31 |    "execution_count": 61,
 32 |    "id": "de7988a7",
 33 |    "metadata": {},
 34 |    "outputs": [],
 35 |    "source": [
 36 |     "df[\"divide_equal_4\"] = pd.qcut(df[\"nums\"], q = 4)\n",
 37 |     "\n",
 38 |     "df[\"divide_equal_cat\"] = pd.qcut(df[\"nums\"], q = 4,labels = [\"awful\", \"bad\", \"average\", \"good\"])"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 66,
 44 |    "id": "65fa7db1",
 45 |    "metadata": {},
 46 |    "outputs": [],
 47 |    "source": [
 48 |     "df[\"nums_cat\"] = pd.qcut(df[\"nums\"], q = 4,labels = [0,1,2,3])"
 49 |    ]
 50 |   },
 51 |   {
 52 |    "cell_type": "code",
 53 |    "execution_count": 69,
 54 |    "id": "b29a92a3",
 55 |    "metadata": {},
 56 |    "outputs": [
 57 |     {
 58 |      "data": {
 59 |       "text/html": [
 60 |        "<div>\n",
 61 |        "<style scoped>\n",
 62 |        "    .dataframe tbody tr th:only-of-type {\n",
 63 |        "        vertical-align: middle;\n",
 64 |        "    }\n",
 65 |        "\n",
 66 |        "    .dataframe tbody tr th {\n",
 67 |        "        vertical-align: top;\n",
 68 |        "    }\n",
 69 |        "\n",
 70 |        "    .dataframe thead th {\n",
 71 |        "        text-align: right;\n",
 72 |        "    }\n",
 73 |        "</style>\n",
 74 |        "<table border=\"1\" class=\"dataframe\">\n",
 75 |        "  <thead>\n",
 76 |        "    <tr style=\"text-align: right;\">\n",
 77 |        "      <th></th>\n",
 78 |        "      <th>nums</th>\n",
 79 |        "      <th>bin</th>\n",
 80 |        "      <th>bin_cat</th>\n",
 81 |        "      <th>divide_equal_4</th>\n",
 82 |        "      <th>divide_equal_cat</th>\n",
 83 |        "      <th>nums_cat</th>\n",
 84 |        "      <th>nums_cat2</th>\n",
 85 |        "    </tr>\n",
 86 |        "  </thead>\n",
 87 |        "  <tbody>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>0</th>\n",
 90 |        "      <td>86</td>\n",
 91 |        "      <td>(80, 99]</td>\n",
 92 |        "      <td>good</td>\n",
 93 |        "      <td>(78.0, 90.0]</td>\n",
 94 |        "      <td>good</td>\n",
 95 |        "      <td>3</td>\n",
 96 |        "      <td>Diamond</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>1</th>\n",
100 |        "      <td>76</td>\n",
101 |        "      <td>(50, 80]</td>\n",
102 |        "      <td>average</td>\n",
103 |        "      <td>(66.0, 78.0]</td>\n",
104 |        "      <td>average</td>\n",
105 |        "      <td>2</td>\n",
106 |        "      <td>Platinum</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>2</th>\n",
110 |        "      <td>31</td>\n",
111 |        "      <td>(15, 50]</td>\n",
112 |        "      <td>bad</td>\n",
113 |        "      <td>(21.0, 66.0]</td>\n",
114 |        "      <td>bad</td>\n",
115 |        "      <td>1</td>\n",
116 |        "      <td>Silver</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>3</th>\n",
120 |        "      <td>80</td>\n",
121 |        "      <td>(50, 80]</td>\n",
122 |        "      <td>average</td>\n",
123 |        "      <td>(78.0, 90.0]</td>\n",
124 |        "      <td>good</td>\n",
125 |        "      <td>3</td>\n",
126 |        "      <td>Platinum</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>4</th>\n",
130 |        "      <td>90</td>\n",
131 |        "      <td>(80, 99]</td>\n",
132 |        "      <td>good</td>\n",
133 |        "      <td>(78.0, 90.0]</td>\n",
134 |        "      <td>good</td>\n",
135 |        "      <td>3</td>\n",
136 |        "      <td>Diamond</td>\n",
137 |        "    </tr>\n",
138 |        "    <tr>\n",
139 |        "      <th>5</th>\n",
140 |        "      <td>71</td>\n",
141 |        "      <td>(50, 80]</td>\n",
142 |        "      <td>average</td>\n",
143 |        "      <td>(66.0, 78.0]</td>\n",
144 |        "      <td>average</td>\n",
145 |        "      <td>2</td>\n",
146 |        "      <td>Platinum</td>\n",
147 |        "    </tr>\n",
148 |        "    <tr>\n",
149 |        "      <th>6</th>\n",
150 |        "      <td>12</td>\n",
151 |        "      <td>(0, 15]</td>\n",
152 |        "      <td>awful</td>\n",
153 |        "      <td>(1.999, 21.0]</td>\n",
154 |        "      <td>awful</td>\n",
155 |        "      <td>0</td>\n",
156 |        "      <td>Silver</td>\n",
157 |        "    </tr>\n",
158 |        "    <tr>\n",
159 |        "      <th>7</th>\n",
160 |        "      <td>20</td>\n",
161 |        "      <td>(15, 50]</td>\n",
162 |        "      <td>bad</td>\n",
163 |        "      <td>(1.999, 21.0]</td>\n",
164 |        "      <td>awful</td>\n",
165 |        "      <td>0</td>\n",
166 |        "      <td>Silver</td>\n",
167 |        "    </tr>\n",
168 |        "    <tr>\n",
169 |        "      <th>8</th>\n",
170 |        "      <td>22</td>\n",
171 |        "      <td>(15, 50]</td>\n",
172 |        "      <td>bad</td>\n",
173 |        "      <td>(21.0, 66.0]</td>\n",
174 |        "      <td>bad</td>\n",
175 |        "      <td>1</td>\n",
176 |        "      <td>Silver</td>\n",
177 |        "    </tr>\n",
178 |        "    <tr>\n",
179 |        "      <th>9</th>\n",
180 |        "      <td>89</td>\n",
181 |        "      <td>(80, 99]</td>\n",
182 |        "      <td>good</td>\n",
183 |        "      <td>(78.0, 90.0]</td>\n",
184 |        "      <td>good</td>\n",
185 |        "      <td>3</td>\n",
186 |        "      <td>Diamond</td>\n",
187 |        "    </tr>\n",
188 |        "    <tr>\n",
189 |        "      <th>10</th>\n",
190 |        "      <td>42</td>\n",
191 |        "      <td>(15, 50]</td>\n",
192 |        "      <td>bad</td>\n",
193 |        "      <td>(21.0, 66.0]</td>\n",
194 |        "      <td>bad</td>\n",
195 |        "      <td>1</td>\n",
196 |        "      <td>Gold</td>\n",
197 |        "    </tr>\n",
198 |        "    <tr>\n",
199 |        "      <th>11</th>\n",
200 |        "      <td>72</td>\n",
201 |        "      <td>(50, 80]</td>\n",
202 |        "      <td>average</td>\n",
203 |        "      <td>(66.0, 78.0]</td>\n",
204 |        "      <td>average</td>\n",
205 |        "      <td>2</td>\n",
206 |        "      <td>Platinum</td>\n",
207 |        "    </tr>\n",
208 |        "    <tr>\n",
209 |        "      <th>12</th>\n",
210 |        "      <td>2</td>\n",
211 |        "      <td>(0, 15]</td>\n",
212 |        "      <td>awful</td>\n",
213 |        "      <td>(1.999, 21.0]</td>\n",
214 |        "      <td>awful</td>\n",
215 |        "      <td>0</td>\n",
216 |        "      <td>Bronze</td>\n",
217 |        "    </tr>\n",
218 |        "    <tr>\n",
219 |        "      <th>13</th>\n",
220 |        "      <td>66</td>\n",
221 |        "      <td>(50, 80]</td>\n",
222 |        "      <td>average</td>\n",
223 |        "      <td>(21.0, 66.0]</td>\n",
224 |        "      <td>bad</td>\n",
225 |        "      <td>1</td>\n",
226 |        "      <td>Gold</td>\n",
227 |        "    </tr>\n",
228 |        "    <tr>\n",
229 |        "      <th>14</th>\n",
230 |        "      <td>9</td>\n",
231 |        "      <td>(0, 15]</td>\n",
232 |        "      <td>awful</td>\n",
233 |        "      <td>(1.999, 21.0]</td>\n",
234 |        "      <td>awful</td>\n",
235 |        "      <td>0</td>\n",
236 |        "      <td>Bronze</td>\n",
237 |        "    </tr>\n",
238 |        "  </tbody>\n",
239 |        "</table>\n",
240 |        "</div>"
241 |       ],
242 |       "text/plain": [
243 |        "    nums       bin  bin_cat divide_equal_4 divide_equal_cat nums_cat nums_cat2\n",
244 |        "0     86  (80, 99]     good   (78.0, 90.0]             good        3   Diamond\n",
245 |        "1     76  (50, 80]  average   (66.0, 78.0]          average        2  Platinum\n",
246 |        "2     31  (15, 50]      bad   (21.0, 66.0]              bad        1    Silver\n",
247 |        "3     80  (50, 80]  average   (78.0, 90.0]             good        3  Platinum\n",
248 |        "4     90  (80, 99]     good   (78.0, 90.0]             good        3   Diamond\n",
249 |        "5     71  (50, 80]  average   (66.0, 78.0]          average        2  Platinum\n",
250 |        "6     12   (0, 15]    awful  (1.999, 21.0]            awful        0    Silver\n",
251 |        "7     20  (15, 50]      bad  (1.999, 21.0]            awful        0    Silver\n",
252 |        "8     22  (15, 50]      bad   (21.0, 66.0]              bad        1    Silver\n",
253 |        "9     89  (80, 99]     good   (78.0, 90.0]             good        3   Diamond\n",
254 |        "10    42  (15, 50]      bad   (21.0, 66.0]              bad        1      Gold\n",
255 |        "11    72  (50, 80]  average   (66.0, 78.0]          average        2  Platinum\n",
256 |        "12     2   (0, 15]    awful  (1.999, 21.0]            awful        0    Bronze\n",
257 |        "13    66  (50, 80]  average   (21.0, 66.0]              bad        1      Gold\n",
258 |        "14     9   (0, 15]    awful  (1.999, 21.0]            awful        0    Bronze"
259 |       ]
260 |      },
261 |      "execution_count": 69,
262 |      "metadata": {},
263 |      "output_type": "execute_result"
264 |     }
265 |    ],
266 |    "source": [
267 |     "bin_labels_5 = ['Bronze', 'Silver', 'Gold', 'Platinum', 'Diamond']\n",
268 |     "df['nums_cat2'] = pd.qcut(df['nums'],\n",
269 |     "                              q=[0, .1, .4, .5, .8, 1],\n",
270 |     "                              labels=bin_labels_5)\n",
271 |     "df"
272 |    ]
273 |   },
274 |   {
275 |    "cell_type": "markdown",
276 |    "id": "fb422c74",
277 |    "metadata": {},
278 |    "source": [
279 |     "https://www.skytowner.com/explore/pandas_qcut_method"
280 |    ]
281 |   },
282 |   {
283 |    "cell_type": "code",
284 |    "execution_count": null,
285 |    "id": "b5223131",
286 |    "metadata": {},
287 |    "outputs": [],
288 |    "source": []
289 |   },
290 |   {
291 |    "cell_type": "code",
292 |    "execution_count": 155,
293 |    "id": "a85167b2",
294 |    "metadata": {},
295 |    "outputs": [],
296 |    "source": []
297 |   },
298 |   {
299 |    "cell_type": "code",
300 |    "execution_count": null,
301 |    "id": "d38e053e",
302 |    "metadata": {},
303 |    "outputs": [],
304 |    "source": []
305 |   }
306 |  ],
307 |  "metadata": {
308 |   "kernelspec": {
309 |    "display_name": "Python 3 (ipykernel)",
310 |    "language": "python",
311 |    "name": "python3"
312 |   },
313 |   "language_info": {
314 |    "codemirror_mode": {
315 |     "name": "ipython",
316 |     "version": 3
317 |    },
318 |    "file_extension": ".py",
319 |    "mimetype": "text/x-python",
320 |    "name": "python",
321 |    "nbconvert_exporter": "python",
322 |    "pygments_lexer": "ipython3",
323 |    "version": "3.9.13"
324 |   }
325 |  },
326 |  "nbformat": 4,
327 |  "nbformat_minor": 5
328 | }
329 | 


--------------------------------------------------------------------------------
/Session3/query_Dataframe.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 13,
  6 |    "id": "05543ee8-86a2-49c8-a5fe-db0ed06a70f5",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>colum_without_space</th>\n",
 31 |        "      <th>column_with_space</th>\n",
 32 |        "    </tr>\n",
 33 |        "  </thead>\n",
 34 |        "  <tbody>\n",
 35 |        "    <tr>\n",
 36 |        "      <th>0</th>\n",
 37 |        "      <td>1</td>\n",
 38 |        "      <td>2</td>\n",
 39 |        "    </tr>\n",
 40 |        "    <tr>\n",
 41 |        "      <th>1</th>\n",
 42 |        "      <td>2</td>\n",
 43 |        "      <td>4</td>\n",
 44 |        "    </tr>\n",
 45 |        "    <tr>\n",
 46 |        "      <th>2</th>\n",
 47 |        "      <td>3</td>\n",
 48 |        "      <td>6</td>\n",
 49 |        "    </tr>\n",
 50 |        "  </tbody>\n",
 51 |        "</table>\n",
 52 |        "</div>"
 53 |       ],
 54 |       "text/plain": [
 55 |        "   colum_without_space  column_with_space\n",
 56 |        "0                    1                  2\n",
 57 |        "1                    2                  4\n",
 58 |        "2                    3                  6"
 59 |       ]
 60 |      },
 61 |      "execution_count": 13,
 62 |      "metadata": {},
 63 |      "output_type": "execute_result"
 64 |     }
 65 |    ],
 66 |    "source": [
 67 |     "import pandas as pd\n",
 68 |     "import numpy as np\n",
 69 |     "\n",
 70 |     "d={\"colum_without_space\":np.array([1,2,3,4,5,6]),\"column_with_space\":np.array([1,2,3,4,5,6])*2}\n",
 71 |     "df=pd.DataFrame(d)\n",
 72 |     "df\n"
 73 |    ]
 74 |   },
 75 |   {
 76 |    "cell_type": "code",
 77 |    "execution_count": 14,
 78 |    "id": "aeeccfd7-e5e7-4a92-8a18-4854cc32cbfa",
 79 |    "metadata": {},
 80 |    "outputs": [
 81 |     {
 82 |      "data": {
 83 |       "text/html": [
 84 |        "<div>\n",
 85 |        "<style scoped>\n",
 86 |        "    .dataframe tbody tr th:only-of-type {\n",
 87 |        "        vertical-align: middle;\n",
 88 |        "    }\n",
 89 |        "\n",
 90 |        "    .dataframe tbody tr th {\n",
 91 |        "        vertical-align: top;\n",
 92 |        "    }\n",
 93 |        "\n",
 94 |        "    .dataframe thead th {\n",
 95 |        "        text-align: right;\n",
 96 |        "    }\n",
 97 |        "</style>\n",
 98 |        "<table border=\"1\" class=\"dataframe\">\n",
 99 |        "  <thead>\n",
100 |        "    <tr style=\"text-align: right;\">\n",
101 |        "      <th></th>\n",
102 |        "      <th>colum_without_space</th>\n",
103 |        "      <th>column_with_space</th>\n",
104 |        "    </tr>\n",
105 |        "  </thead>\n",
106 |        "  <tbody>\n",
107 |        "    <tr>\n",
108 |        "      <th>0</th>\n",
109 |        "      <td>1</td>\n",
110 |        "      <td>2</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>1</th>\n",
114 |        "      <td>2</td>\n",
115 |        "      <td>4</td>\n",
116 |        "    </tr>\n",
117 |        "    <tr>\n",
118 |        "      <th>2</th>\n",
119 |        "      <td>3</td>\n",
120 |        "      <td>6</td>\n",
121 |        "    </tr>\n",
122 |        "    <tr>\n",
123 |        "      <th>3</th>\n",
124 |        "      <td>4</td>\n",
125 |        "      <td>8</td>\n",
126 |        "    </tr>\n",
127 |        "    <tr>\n",
128 |        "      <th>4</th>\n",
129 |        "      <td>5</td>\n",
130 |        "      <td>10</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>5</th>\n",
134 |        "      <td>6</td>\n",
135 |        "      <td>12</td>\n",
136 |        "    </tr>\n",
137 |        "  </tbody>\n",
138 |        "</table>\n",
139 |        "</div>"
140 |       ],
141 |       "text/plain": [
142 |        "   colum_without_space  column_with_space\n",
143 |        "0                    1                  2\n",
144 |        "1                    2                  4\n",
145 |        "2                    3                  6\n",
146 |        "3                    4                  8\n",
147 |        "4                    5                 10\n",
148 |        "5                    6                 12"
149 |       ]
150 |      },
151 |      "execution_count": 14,
152 |      "metadata": {},
153 |      "output_type": "execute_result"
154 |     }
155 |    ],
156 |    "source": [
157 |     "df.query(\"colum_without_space<4\")"
158 |    ]
159 |   },
160 |   {
161 |    "cell_type": "code",
162 |    "execution_count": 15,
163 |    "id": "90e00738-bd00-4deb-a98f-0f41f0666f9c",
164 |    "metadata": {},
165 |    "outputs": [
166 |     {
167 |      "data": {
168 |       "text/html": [
169 |        "<div>\n",
170 |        "<style scoped>\n",
171 |        "    .dataframe tbody tr th:only-of-type {\n",
172 |        "        vertical-align: middle;\n",
173 |        "    }\n",
174 |        "\n",
175 |        "    .dataframe tbody tr th {\n",
176 |        "        vertical-align: top;\n",
177 |        "    }\n",
178 |        "\n",
179 |        "    .dataframe thead th {\n",
180 |        "        text-align: right;\n",
181 |        "    }\n",
182 |        "</style>\n",
183 |        "<table border=\"1\" class=\"dataframe\">\n",
184 |        "  <thead>\n",
185 |        "    <tr style=\"text-align: right;\">\n",
186 |        "      <th></th>\n",
187 |        "      <th>colum_without_space</th>\n",
188 |        "      <th>column_with_space</th>\n",
189 |        "    </tr>\n",
190 |        "  </thead>\n",
191 |        "  <tbody>\n",
192 |        "    <tr>\n",
193 |        "      <th>0</th>\n",
194 |        "      <td>1</td>\n",
195 |        "      <td>2</td>\n",
196 |        "    </tr>\n",
197 |        "    <tr>\n",
198 |        "      <th>1</th>\n",
199 |        "      <td>2</td>\n",
200 |        "      <td>4</td>\n",
201 |        "    </tr>\n",
202 |        "    <tr>\n",
203 |        "      <th>2</th>\n",
204 |        "      <td>3</td>\n",
205 |        "      <td>6</td>\n",
206 |        "    </tr>\n",
207 |        "  </tbody>\n",
208 |        "</table>\n",
209 |        "</div>"
210 |       ],
211 |       "text/plain": [
212 |        "   colum_without_space  column_with_space\n",
213 |        "0                    1                  2\n",
214 |        "1                    2                  4\n",
215 |        "2                    3                  6"
216 |       ]
217 |      },
218 |      "execution_count": 15,
219 |      "metadata": {},
220 |      "output_type": "execute_result"
221 |     }
222 |    ],
223 |    "source": [
224 |     "df.query(\"column_with_space<8\")"
225 |    ]
226 |   },
227 |   {
228 |    "cell_type": "code",
229 |    "execution_count": null,
230 |    "id": "57244ce6-8110-4566-8045-e4e62be938c2",
231 |    "metadata": {},
232 |    "outputs": [],
233 |    "source": []
234 |   }
235 |  ],
236 |  "metadata": {
237 |   "kernelspec": {
238 |    "display_name": "Python 3 (ipykernel)",
239 |    "language": "python",
240 |    "name": "python3"
241 |   },
242 |   "language_info": {
243 |    "codemirror_mode": {
244 |     "name": "ipython",
245 |     "version": 3
246 |    },
247 |    "file_extension": ".py",
248 |    "mimetype": "text/x-python",
249 |    "name": "python",
250 |    "nbconvert_exporter": "python",
251 |    "pygments_lexer": "ipython3",
252 |    "version": "3.9.12"
253 |   }
254 |  },
255 |  "nbformat": 4,
256 |  "nbformat_minor": 5
257 | }
258 | 


--------------------------------------------------------------------------------
/Session3/transform sum pandas column.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "51074644",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>orderid</th>\n",
 31 |        "      <th>item</th>\n",
 32 |        "    </tr>\n",
 33 |        "  </thead>\n",
 34 |        "  <tbody>\n",
 35 |        "    <tr>\n",
 36 |        "      <th>0</th>\n",
 37 |        "      <td>1</td>\n",
 38 |        "      <td>10.0</td>\n",
 39 |        "    </tr>\n",
 40 |        "    <tr>\n",
 41 |        "      <th>1</th>\n",
 42 |        "      <td>1</td>\n",
 43 |        "      <td>120.0</td>\n",
 44 |        "    </tr>\n",
 45 |        "    <tr>\n",
 46 |        "      <th>2</th>\n",
 47 |        "      <td>1</td>\n",
 48 |        "      <td>130.0</td>\n",
 49 |        "    </tr>\n",
 50 |        "    <tr>\n",
 51 |        "      <th>3</th>\n",
 52 |        "      <td>2</td>\n",
 53 |        "      <td>200.0</td>\n",
 54 |        "    </tr>\n",
 55 |        "    <tr>\n",
 56 |        "      <th>4</th>\n",
 57 |        "      <td>2</td>\n",
 58 |        "      <td>300.0</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>5</th>\n",
 62 |        "      <td>3</td>\n",
 63 |        "      <td>550.0</td>\n",
 64 |        "    </tr>\n",
 65 |        "    <tr>\n",
 66 |        "      <th>6</th>\n",
 67 |        "      <td>4</td>\n",
 68 |        "      <td>12.3</td>\n",
 69 |        "    </tr>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>7</th>\n",
 72 |        "      <td>5</td>\n",
 73 |        "      <td>200.0</td>\n",
 74 |        "    </tr>\n",
 75 |        "  </tbody>\n",
 76 |        "</table>\n",
 77 |        "</div>"
 78 |       ],
 79 |       "text/plain": [
 80 |        "   orderid   item\n",
 81 |        "0        1   10.0\n",
 82 |        "1        1  120.0\n",
 83 |        "2        1  130.0\n",
 84 |        "3        2  200.0\n",
 85 |        "4        2  300.0\n",
 86 |        "5        3  550.0\n",
 87 |        "6        4   12.3\n",
 88 |        "7        5  200.0"
 89 |       ]
 90 |      },
 91 |      "execution_count": 2,
 92 |      "metadata": {},
 93 |      "output_type": "execute_result"
 94 |     }
 95 |    ],
 96 |    "source": [
 97 |     "import pandas as pd\n",
 98 |     "d = {\"orderid\":[1, 1, 1, 2, 2, 3, 4, 5], \"item\":[10, 120, 130, 200, 300, 550, 12.3, 200]}\n",
 99 |     "df = pd.DataFrame(d)\n",
100 |     "df\n",
101 |     "\n"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": 3,
107 |    "id": "b4acf6ed",
108 |    "metadata": {},
109 |    "outputs": [
110 |     {
111 |      "name": "stdout",
112 |      "output_type": "stream",
113 |      "text": [
114 |       "This is the output we want to aggregate to the original df\n"
115 |      ]
116 |     },
117 |     {
118 |      "data": {
119 |       "text/html": [
120 |        "<div>\n",
121 |        "<style scoped>\n",
122 |        "    .dataframe tbody tr th:only-of-type {\n",
123 |        "        vertical-align: middle;\n",
124 |        "    }\n",
125 |        "\n",
126 |        "    .dataframe tbody tr th {\n",
127 |        "        vertical-align: top;\n",
128 |        "    }\n",
129 |        "\n",
130 |        "    .dataframe thead th {\n",
131 |        "        text-align: right;\n",
132 |        "    }\n",
133 |        "</style>\n",
134 |        "<table border=\"1\" class=\"dataframe\">\n",
135 |        "  <thead>\n",
136 |        "    <tr style=\"text-align: right;\">\n",
137 |        "      <th></th>\n",
138 |        "      <th>item</th>\n",
139 |        "    </tr>\n",
140 |        "    <tr>\n",
141 |        "      <th>orderid</th>\n",
142 |        "      <th></th>\n",
143 |        "    </tr>\n",
144 |        "  </thead>\n",
145 |        "  <tbody>\n",
146 |        "    <tr>\n",
147 |        "      <th>1</th>\n",
148 |        "      <td>260.0</td>\n",
149 |        "    </tr>\n",
150 |        "    <tr>\n",
151 |        "      <th>2</th>\n",
152 |        "      <td>500.0</td>\n",
153 |        "    </tr>\n",
154 |        "    <tr>\n",
155 |        "      <th>3</th>\n",
156 |        "      <td>550.0</td>\n",
157 |        "    </tr>\n",
158 |        "    <tr>\n",
159 |        "      <th>4</th>\n",
160 |        "      <td>12.3</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>5</th>\n",
164 |        "      <td>200.0</td>\n",
165 |        "    </tr>\n",
166 |        "  </tbody>\n",
167 |        "</table>\n",
168 |        "</div>"
169 |       ],
170 |       "text/plain": [
171 |        "          item\n",
172 |        "orderid       \n",
173 |        "1        260.0\n",
174 |        "2        500.0\n",
175 |        "3        550.0\n",
176 |        "4         12.3\n",
177 |        "5        200.0"
178 |       ]
179 |      },
180 |      "execution_count": 3,
181 |      "metadata": {},
182 |      "output_type": "execute_result"
183 |     }
184 |    ],
185 |    "source": [
186 |     "print(\"This is the output we want to aggregate to the original df\")\n",
187 |     "df.groupby(\"orderid\")[\"item\"].sum().to_frame()\n"
188 |    ]
189 |   },
190 |   {
191 |    "cell_type": "code",
192 |    "execution_count": 4,
193 |    "id": "f2904919",
194 |    "metadata": {},
195 |    "outputs": [
196 |     {
197 |      "data": {
198 |       "text/html": [
199 |        "<div>\n",
200 |        "<style scoped>\n",
201 |        "    .dataframe tbody tr th:only-of-type {\n",
202 |        "        vertical-align: middle;\n",
203 |        "    }\n",
204 |        "\n",
205 |        "    .dataframe tbody tr th {\n",
206 |        "        vertical-align: top;\n",
207 |        "    }\n",
208 |        "\n",
209 |        "    .dataframe thead th {\n",
210 |        "        text-align: right;\n",
211 |        "    }\n",
212 |        "</style>\n",
213 |        "<table border=\"1\" class=\"dataframe\">\n",
214 |        "  <thead>\n",
215 |        "    <tr style=\"text-align: right;\">\n",
216 |        "      <th></th>\n",
217 |        "      <th>orderid</th>\n",
218 |        "      <th>item</th>\n",
219 |        "      <th>total_items_sold</th>\n",
220 |        "    </tr>\n",
221 |        "  </thead>\n",
222 |        "  <tbody>\n",
223 |        "    <tr>\n",
224 |        "      <th>0</th>\n",
225 |        "      <td>1</td>\n",
226 |        "      <td>10.0</td>\n",
227 |        "      <td>260.0</td>\n",
228 |        "    </tr>\n",
229 |        "    <tr>\n",
230 |        "      <th>1</th>\n",
231 |        "      <td>1</td>\n",
232 |        "      <td>120.0</td>\n",
233 |        "      <td>260.0</td>\n",
234 |        "    </tr>\n",
235 |        "    <tr>\n",
236 |        "      <th>2</th>\n",
237 |        "      <td>1</td>\n",
238 |        "      <td>130.0</td>\n",
239 |        "      <td>260.0</td>\n",
240 |        "    </tr>\n",
241 |        "    <tr>\n",
242 |        "      <th>3</th>\n",
243 |        "      <td>2</td>\n",
244 |        "      <td>200.0</td>\n",
245 |        "      <td>500.0</td>\n",
246 |        "    </tr>\n",
247 |        "    <tr>\n",
248 |        "      <th>4</th>\n",
249 |        "      <td>2</td>\n",
250 |        "      <td>300.0</td>\n",
251 |        "      <td>500.0</td>\n",
252 |        "    </tr>\n",
253 |        "    <tr>\n",
254 |        "      <th>5</th>\n",
255 |        "      <td>3</td>\n",
256 |        "      <td>550.0</td>\n",
257 |        "      <td>550.0</td>\n",
258 |        "    </tr>\n",
259 |        "    <tr>\n",
260 |        "      <th>6</th>\n",
261 |        "      <td>4</td>\n",
262 |        "      <td>12.3</td>\n",
263 |        "      <td>12.3</td>\n",
264 |        "    </tr>\n",
265 |        "    <tr>\n",
266 |        "      <th>7</th>\n",
267 |        "      <td>5</td>\n",
268 |        "      <td>200.0</td>\n",
269 |        "      <td>200.0</td>\n",
270 |        "    </tr>\n",
271 |        "  </tbody>\n",
272 |        "</table>\n",
273 |        "</div>"
274 |       ],
275 |       "text/plain": [
276 |        "   orderid   item  total_items_sold\n",
277 |        "0        1   10.0             260.0\n",
278 |        "1        1  120.0             260.0\n",
279 |        "2        1  130.0             260.0\n",
280 |        "3        2  200.0             500.0\n",
281 |        "4        2  300.0             500.0\n",
282 |        "5        3  550.0             550.0\n",
283 |        "6        4   12.3              12.3\n",
284 |        "7        5  200.0             200.0"
285 |       ]
286 |      },
287 |      "execution_count": 4,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "df[\"total_items_sold\"] = df.groupby(\"orderid\")[\"item\"].transform(sum)\n",
294 |     "df"
295 |    ]
296 |   },
297 |   {
298 |    "cell_type": "code",
299 |    "execution_count": null,
300 |    "id": "51f5e41f",
301 |    "metadata": {},
302 |    "outputs": [],
303 |    "source": []
304 |   }
305 |  ],
306 |  "metadata": {
307 |   "kernelspec": {
308 |    "display_name": "Python 3 (ipykernel)",
309 |    "language": "python",
310 |    "name": "python3"
311 |   },
312 |   "language_info": {
313 |    "codemirror_mode": {
314 |     "name": "ipython",
315 |     "version": 3
316 |    },
317 |    "file_extension": ".py",
318 |    "mimetype": "text/x-python",
319 |    "name": "python",
320 |    "nbconvert_exporter": "python",
321 |    "pygments_lexer": "ipython3",
322 |    "version": "3.9.13"
323 |   }
324 |  },
325 |  "nbformat": 4,
326 |  "nbformat_minor": 5
327 | }
328 | 


--------------------------------------------------------------------------------
/Session4/load autotime for every cell runtime and select_dtypes.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "ba2de180",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>department</th>\n",
 31 |        "      <th>promoted</th>\n",
 32 |        "      <th>review</th>\n",
 33 |        "      <th>projects</th>\n",
 34 |        "      <th>salary</th>\n",
 35 |        "      <th>tenure</th>\n",
 36 |        "      <th>satisfaction</th>\n",
 37 |        "      <th>bonus</th>\n",
 38 |        "      <th>avg_hrs_month</th>\n",
 39 |        "      <th>left</th>\n",
 40 |        "    </tr>\n",
 41 |        "  </thead>\n",
 42 |        "  <tbody>\n",
 43 |        "    <tr>\n",
 44 |        "      <th>0</th>\n",
 45 |        "      <td>operations</td>\n",
 46 |        "      <td>0</td>\n",
 47 |        "      <td>0.577569</td>\n",
 48 |        "      <td>3</td>\n",
 49 |        "      <td>low</td>\n",
 50 |        "      <td>5.0</td>\n",
 51 |        "      <td>0.626759</td>\n",
 52 |        "      <td>0</td>\n",
 53 |        "      <td>180.866070</td>\n",
 54 |        "      <td>no</td>\n",
 55 |        "    </tr>\n",
 56 |        "    <tr>\n",
 57 |        "      <th>1</th>\n",
 58 |        "      <td>operations</td>\n",
 59 |        "      <td>0</td>\n",
 60 |        "      <td>0.751900</td>\n",
 61 |        "      <td>3</td>\n",
 62 |        "      <td>medium</td>\n",
 63 |        "      <td>6.0</td>\n",
 64 |        "      <td>0.443679</td>\n",
 65 |        "      <td>0</td>\n",
 66 |        "      <td>182.708149</td>\n",
 67 |        "      <td>no</td>\n",
 68 |        "    </tr>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>2</th>\n",
 71 |        "      <td>support</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "      <td>0.722548</td>\n",
 74 |        "      <td>3</td>\n",
 75 |        "      <td>medium</td>\n",
 76 |        "      <td>6.0</td>\n",
 77 |        "      <td>0.446823</td>\n",
 78 |        "      <td>0</td>\n",
 79 |        "      <td>184.416084</td>\n",
 80 |        "      <td>no</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>3</th>\n",
 84 |        "      <td>logistics</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>0.675158</td>\n",
 87 |        "      <td>4</td>\n",
 88 |        "      <td>high</td>\n",
 89 |        "      <td>8.0</td>\n",
 90 |        "      <td>0.440139</td>\n",
 91 |        "      <td>0</td>\n",
 92 |        "      <td>188.707545</td>\n",
 93 |        "      <td>no</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>4</th>\n",
 97 |        "      <td>sales</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "      <td>0.676203</td>\n",
100 |        "      <td>3</td>\n",
101 |        "      <td>high</td>\n",
102 |        "      <td>5.0</td>\n",
103 |        "      <td>0.577607</td>\n",
104 |        "      <td>1</td>\n",
105 |        "      <td>179.821083</td>\n",
106 |        "      <td>no</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>...</th>\n",
110 |        "      <td>...</td>\n",
111 |        "      <td>...</td>\n",
112 |        "      <td>...</td>\n",
113 |        "      <td>...</td>\n",
114 |        "      <td>...</td>\n",
115 |        "      <td>...</td>\n",
116 |        "      <td>...</td>\n",
117 |        "      <td>...</td>\n",
118 |        "      <td>...</td>\n",
119 |        "      <td>...</td>\n",
120 |        "    </tr>\n",
121 |        "    <tr>\n",
122 |        "      <th>9535</th>\n",
123 |        "      <td>operations</td>\n",
124 |        "      <td>0</td>\n",
125 |        "      <td>0.610988</td>\n",
126 |        "      <td>4</td>\n",
127 |        "      <td>medium</td>\n",
128 |        "      <td>8.0</td>\n",
129 |        "      <td>0.543641</td>\n",
130 |        "      <td>0</td>\n",
131 |        "      <td>188.155738</td>\n",
132 |        "      <td>yes</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>9536</th>\n",
136 |        "      <td>logistics</td>\n",
137 |        "      <td>0</td>\n",
138 |        "      <td>0.746887</td>\n",
139 |        "      <td>3</td>\n",
140 |        "      <td>medium</td>\n",
141 |        "      <td>8.0</td>\n",
142 |        "      <td>0.549048</td>\n",
143 |        "      <td>0</td>\n",
144 |        "      <td>188.176164</td>\n",
145 |        "      <td>yes</td>\n",
146 |        "    </tr>\n",
147 |        "    <tr>\n",
148 |        "      <th>9537</th>\n",
149 |        "      <td>operations</td>\n",
150 |        "      <td>0</td>\n",
151 |        "      <td>0.557980</td>\n",
152 |        "      <td>3</td>\n",
153 |        "      <td>low</td>\n",
154 |        "      <td>7.0</td>\n",
155 |        "      <td>0.705425</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>186.531008</td>\n",
158 |        "      <td>yes</td>\n",
159 |        "    </tr>\n",
160 |        "    <tr>\n",
161 |        "      <th>9538</th>\n",
162 |        "      <td>IT</td>\n",
163 |        "      <td>0</td>\n",
164 |        "      <td>0.584446</td>\n",
165 |        "      <td>4</td>\n",
166 |        "      <td>medium</td>\n",
167 |        "      <td>8.0</td>\n",
168 |        "      <td>0.607287</td>\n",
169 |        "      <td>1</td>\n",
170 |        "      <td>187.641370</td>\n",
171 |        "      <td>yes</td>\n",
172 |        "    </tr>\n",
173 |        "    <tr>\n",
174 |        "      <th>9539</th>\n",
175 |        "      <td>finance</td>\n",
176 |        "      <td>0</td>\n",
177 |        "      <td>0.626373</td>\n",
178 |        "      <td>3</td>\n",
179 |        "      <td>low</td>\n",
180 |        "      <td>7.0</td>\n",
181 |        "      <td>0.706455</td>\n",
182 |        "      <td>1</td>\n",
183 |        "      <td>185.920934</td>\n",
184 |        "      <td>yes</td>\n",
185 |        "    </tr>\n",
186 |        "  </tbody>\n",
187 |        "</table>\n",
188 |        "<p>9540 rows × 10 columns</p>\n",
189 |        "</div>"
190 |       ],
191 |       "text/plain": [
192 |        "      department  promoted    review  projects  salary  tenure  satisfaction  \\\n",
193 |        "0     operations         0  0.577569         3     low     5.0      0.626759   \n",
194 |        "1     operations         0  0.751900         3  medium     6.0      0.443679   \n",
195 |        "2        support         0  0.722548         3  medium     6.0      0.446823   \n",
196 |        "3      logistics         0  0.675158         4    high     8.0      0.440139   \n",
197 |        "4          sales         0  0.676203         3    high     5.0      0.577607   \n",
198 |        "...          ...       ...       ...       ...     ...     ...           ...   \n",
199 |        "9535  operations         0  0.610988         4  medium     8.0      0.543641   \n",
200 |        "9536   logistics         0  0.746887         3  medium     8.0      0.549048   \n",
201 |        "9537  operations         0  0.557980         3     low     7.0      0.705425   \n",
202 |        "9538          IT         0  0.584446         4  medium     8.0      0.607287   \n",
203 |        "9539     finance         0  0.626373         3     low     7.0      0.706455   \n",
204 |        "\n",
205 |        "      bonus  avg_hrs_month left  \n",
206 |        "0         0     180.866070   no  \n",
207 |        "1         0     182.708149   no  \n",
208 |        "2         0     184.416084   no  \n",
209 |        "3         0     188.707545   no  \n",
210 |        "4         1     179.821083   no  \n",
211 |        "...     ...            ...  ...  \n",
212 |        "9535      0     188.155738  yes  \n",
213 |        "9536      0     188.176164  yes  \n",
214 |        "9537      0     186.531008  yes  \n",
215 |        "9538      1     187.641370  yes  \n",
216 |        "9539      1     185.920934  yes  \n",
217 |        "\n",
218 |        "[9540 rows x 10 columns]"
219 |       ]
220 |      },
221 |      "execution_count": 1,
222 |      "metadata": {},
223 |      "output_type": "execute_result"
224 |     },
225 |     {
226 |      "name": "stdout",
227 |      "output_type": "stream",
228 |      "text": [
229 |       "time: 29.1 ms (started: 2023-03-26 23:09:11 +03:00)\n"
230 |      ]
231 |     }
232 |    ],
233 |    "source": [
234 |     "import pandas as pd\n",
235 |     "import numpy as np\n",
236 |     "\n",
237 |     "import autotime\n",
238 |     "\n",
239 |     "%load_ext autotime\n",
240 |     "\n",
241 |     "df=pd.read_csv(\"employee_churn_data.csv\")\n",
242 |     "df"
243 |    ]
244 |   },
245 |   {
246 |    "cell_type": "code",
247 |    "execution_count": 5,
248 |    "id": "e119ba3b",
249 |    "metadata": {},
250 |    "outputs": [
251 |     {
252 |      "name": "stdout",
253 |      "output_type": "stream",
254 |      "text": [
255 |       "<class 'pandas.core.frame.DataFrame'>\n",
256 |       "RangeIndex: 9540 entries, 0 to 9539\n",
257 |       "Data columns (total 10 columns):\n",
258 |       " #   Column         Non-Null Count  Dtype  \n",
259 |       "---  ------         --------------  -----  \n",
260 |       " 0   department     9540 non-null   object \n",
261 |       " 1   promoted       9540 non-null   int64  \n",
262 |       " 2   review         9540 non-null   float64\n",
263 |       " 3   projects       9540 non-null   int64  \n",
264 |       " 4   salary         9540 non-null   object \n",
265 |       " 5   tenure         9540 non-null   float64\n",
266 |       " 6   satisfaction   9540 non-null   float64\n",
267 |       " 7   bonus          9540 non-null   int64  \n",
268 |       " 8   avg_hrs_month  9540 non-null   float64\n",
269 |       " 9   left           9540 non-null   object \n",
270 |       "dtypes: float64(4), int64(3), object(3)\n",
271 |       "memory usage: 745.4+ KB\n",
272 |       "time: 16.9 ms (started: 2023-03-26 23:09:43 +03:00)\n"
273 |      ]
274 |     }
275 |    ],
276 |    "source": [
277 |     "df.info()"
278 |    ]
279 |   },
280 |   {
281 |    "cell_type": "code",
282 |    "execution_count": 2,
283 |    "id": "ca9b468f",
284 |    "metadata": {},
285 |    "outputs": [
286 |     {
287 |      "data": {
288 |       "text/html": [
289 |        "<div>\n",
290 |        "<style scoped>\n",
291 |        "    .dataframe tbody tr th:only-of-type {\n",
292 |        "        vertical-align: middle;\n",
293 |        "    }\n",
294 |        "\n",
295 |        "    .dataframe tbody tr th {\n",
296 |        "        vertical-align: top;\n",
297 |        "    }\n",
298 |        "\n",
299 |        "    .dataframe thead th {\n",
300 |        "        text-align: right;\n",
301 |        "    }\n",
302 |        "</style>\n",
303 |        "<table border=\"1\" class=\"dataframe\">\n",
304 |        "  <thead>\n",
305 |        "    <tr style=\"text-align: right;\">\n",
306 |        "      <th></th>\n",
307 |        "      <th>promoted</th>\n",
308 |        "      <th>review</th>\n",
309 |        "      <th>projects</th>\n",
310 |        "      <th>tenure</th>\n",
311 |        "      <th>satisfaction</th>\n",
312 |        "      <th>bonus</th>\n",
313 |        "      <th>avg_hrs_month</th>\n",
314 |        "    </tr>\n",
315 |        "  </thead>\n",
316 |        "  <tbody>\n",
317 |        "    <tr>\n",
318 |        "      <th>0</th>\n",
319 |        "      <td>0</td>\n",
320 |        "      <td>0.577569</td>\n",
321 |        "      <td>3</td>\n",
322 |        "      <td>5.0</td>\n",
323 |        "      <td>0.626759</td>\n",
324 |        "      <td>0</td>\n",
325 |        "      <td>180.866070</td>\n",
326 |        "    </tr>\n",
327 |        "    <tr>\n",
328 |        "      <th>1</th>\n",
329 |        "      <td>0</td>\n",
330 |        "      <td>0.751900</td>\n",
331 |        "      <td>3</td>\n",
332 |        "      <td>6.0</td>\n",
333 |        "      <td>0.443679</td>\n",
334 |        "      <td>0</td>\n",
335 |        "      <td>182.708149</td>\n",
336 |        "    </tr>\n",
337 |        "    <tr>\n",
338 |        "      <th>2</th>\n",
339 |        "      <td>0</td>\n",
340 |        "      <td>0.722548</td>\n",
341 |        "      <td>3</td>\n",
342 |        "      <td>6.0</td>\n",
343 |        "      <td>0.446823</td>\n",
344 |        "      <td>0</td>\n",
345 |        "      <td>184.416084</td>\n",
346 |        "    </tr>\n",
347 |        "    <tr>\n",
348 |        "      <th>3</th>\n",
349 |        "      <td>0</td>\n",
350 |        "      <td>0.675158</td>\n",
351 |        "      <td>4</td>\n",
352 |        "      <td>8.0</td>\n",
353 |        "      <td>0.440139</td>\n",
354 |        "      <td>0</td>\n",
355 |        "      <td>188.707545</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>4</th>\n",
359 |        "      <td>0</td>\n",
360 |        "      <td>0.676203</td>\n",
361 |        "      <td>3</td>\n",
362 |        "      <td>5.0</td>\n",
363 |        "      <td>0.577607</td>\n",
364 |        "      <td>1</td>\n",
365 |        "      <td>179.821083</td>\n",
366 |        "    </tr>\n",
367 |        "    <tr>\n",
368 |        "      <th>...</th>\n",
369 |        "      <td>...</td>\n",
370 |        "      <td>...</td>\n",
371 |        "      <td>...</td>\n",
372 |        "      <td>...</td>\n",
373 |        "      <td>...</td>\n",
374 |        "      <td>...</td>\n",
375 |        "      <td>...</td>\n",
376 |        "    </tr>\n",
377 |        "    <tr>\n",
378 |        "      <th>9535</th>\n",
379 |        "      <td>0</td>\n",
380 |        "      <td>0.610988</td>\n",
381 |        "      <td>4</td>\n",
382 |        "      <td>8.0</td>\n",
383 |        "      <td>0.543641</td>\n",
384 |        "      <td>0</td>\n",
385 |        "      <td>188.155738</td>\n",
386 |        "    </tr>\n",
387 |        "    <tr>\n",
388 |        "      <th>9536</th>\n",
389 |        "      <td>0</td>\n",
390 |        "      <td>0.746887</td>\n",
391 |        "      <td>3</td>\n",
392 |        "      <td>8.0</td>\n",
393 |        "      <td>0.549048</td>\n",
394 |        "      <td>0</td>\n",
395 |        "      <td>188.176164</td>\n",
396 |        "    </tr>\n",
397 |        "    <tr>\n",
398 |        "      <th>9537</th>\n",
399 |        "      <td>0</td>\n",
400 |        "      <td>0.557980</td>\n",
401 |        "      <td>3</td>\n",
402 |        "      <td>7.0</td>\n",
403 |        "      <td>0.705425</td>\n",
404 |        "      <td>0</td>\n",
405 |        "      <td>186.531008</td>\n",
406 |        "    </tr>\n",
407 |        "    <tr>\n",
408 |        "      <th>9538</th>\n",
409 |        "      <td>0</td>\n",
410 |        "      <td>0.584446</td>\n",
411 |        "      <td>4</td>\n",
412 |        "      <td>8.0</td>\n",
413 |        "      <td>0.607287</td>\n",
414 |        "      <td>1</td>\n",
415 |        "      <td>187.641370</td>\n",
416 |        "    </tr>\n",
417 |        "    <tr>\n",
418 |        "      <th>9539</th>\n",
419 |        "      <td>0</td>\n",
420 |        "      <td>0.626373</td>\n",
421 |        "      <td>3</td>\n",
422 |        "      <td>7.0</td>\n",
423 |        "      <td>0.706455</td>\n",
424 |        "      <td>1</td>\n",
425 |        "      <td>185.920934</td>\n",
426 |        "    </tr>\n",
427 |        "  </tbody>\n",
428 |        "</table>\n",
429 |        "<p>9540 rows × 7 columns</p>\n",
430 |        "</div>"
431 |       ],
432 |       "text/plain": [
433 |        "      promoted    review  projects  tenure  satisfaction  bonus  avg_hrs_month\n",
434 |        "0            0  0.577569         3     5.0      0.626759      0     180.866070\n",
435 |        "1            0  0.751900         3     6.0      0.443679      0     182.708149\n",
436 |        "2            0  0.722548         3     6.0      0.446823      0     184.416084\n",
437 |        "3            0  0.675158         4     8.0      0.440139      0     188.707545\n",
438 |        "4            0  0.676203         3     5.0      0.577607      1     179.821083\n",
439 |        "...        ...       ...       ...     ...           ...    ...            ...\n",
440 |        "9535         0  0.610988         4     8.0      0.543641      0     188.155738\n",
441 |        "9536         0  0.746887         3     8.0      0.549048      0     188.176164\n",
442 |        "9537         0  0.557980         3     7.0      0.705425      0     186.531008\n",
443 |        "9538         0  0.584446         4     8.0      0.607287      1     187.641370\n",
444 |        "9539         0  0.626373         3     7.0      0.706455      1     185.920934\n",
445 |        "\n",
446 |        "[9540 rows x 7 columns]"
447 |       ]
448 |      },
449 |      "execution_count": 2,
450 |      "metadata": {},
451 |      "output_type": "execute_result"
452 |     },
453 |     {
454 |      "name": "stdout",
455 |      "output_type": "stream",
456 |      "text": [
457 |       "time: 14.4 ms (started: 2023-03-26 23:09:24 +03:00)\n"
458 |      ]
459 |     }
460 |    ],
461 |    "source": [
462 |     "df.select_dtypes(include=['int64',\"float64\"])"
463 |    ]
464 |   },
465 |   {
466 |    "cell_type": "code",
467 |    "execution_count": 4,
468 |    "id": "752a65a7",
469 |    "metadata": {},
470 |    "outputs": [
471 |     {
472 |      "data": {
473 |       "text/html": [
474 |        "<div>\n",
475 |        "<style scoped>\n",
476 |        "    .dataframe tbody tr th:only-of-type {\n",
477 |        "        vertical-align: middle;\n",
478 |        "    }\n",
479 |        "\n",
480 |        "    .dataframe tbody tr th {\n",
481 |        "        vertical-align: top;\n",
482 |        "    }\n",
483 |        "\n",
484 |        "    .dataframe thead th {\n",
485 |        "        text-align: right;\n",
486 |        "    }\n",
487 |        "</style>\n",
488 |        "<table border=\"1\" class=\"dataframe\">\n",
489 |        "  <thead>\n",
490 |        "    <tr style=\"text-align: right;\">\n",
491 |        "      <th></th>\n",
492 |        "      <th>promoted</th>\n",
493 |        "      <th>review</th>\n",
494 |        "      <th>projects</th>\n",
495 |        "      <th>tenure</th>\n",
496 |        "      <th>satisfaction</th>\n",
497 |        "      <th>bonus</th>\n",
498 |        "      <th>avg_hrs_month</th>\n",
499 |        "    </tr>\n",
500 |        "  </thead>\n",
501 |        "  <tbody>\n",
502 |        "    <tr>\n",
503 |        "      <th>0</th>\n",
504 |        "      <td>0</td>\n",
505 |        "      <td>0.577569</td>\n",
506 |        "      <td>3</td>\n",
507 |        "      <td>5.0</td>\n",
508 |        "      <td>0.626759</td>\n",
509 |        "      <td>0</td>\n",
510 |        "      <td>180.866070</td>\n",
511 |        "    </tr>\n",
512 |        "    <tr>\n",
513 |        "      <th>1</th>\n",
514 |        "      <td>0</td>\n",
515 |        "      <td>0.751900</td>\n",
516 |        "      <td>3</td>\n",
517 |        "      <td>6.0</td>\n",
518 |        "      <td>0.443679</td>\n",
519 |        "      <td>0</td>\n",
520 |        "      <td>182.708149</td>\n",
521 |        "    </tr>\n",
522 |        "    <tr>\n",
523 |        "      <th>2</th>\n",
524 |        "      <td>0</td>\n",
525 |        "      <td>0.722548</td>\n",
526 |        "      <td>3</td>\n",
527 |        "      <td>6.0</td>\n",
528 |        "      <td>0.446823</td>\n",
529 |        "      <td>0</td>\n",
530 |        "      <td>184.416084</td>\n",
531 |        "    </tr>\n",
532 |        "    <tr>\n",
533 |        "      <th>3</th>\n",
534 |        "      <td>0</td>\n",
535 |        "      <td>0.675158</td>\n",
536 |        "      <td>4</td>\n",
537 |        "      <td>8.0</td>\n",
538 |        "      <td>0.440139</td>\n",
539 |        "      <td>0</td>\n",
540 |        "      <td>188.707545</td>\n",
541 |        "    </tr>\n",
542 |        "    <tr>\n",
543 |        "      <th>4</th>\n",
544 |        "      <td>0</td>\n",
545 |        "      <td>0.676203</td>\n",
546 |        "      <td>3</td>\n",
547 |        "      <td>5.0</td>\n",
548 |        "      <td>0.577607</td>\n",
549 |        "      <td>1</td>\n",
550 |        "      <td>179.821083</td>\n",
551 |        "    </tr>\n",
552 |        "    <tr>\n",
553 |        "      <th>...</th>\n",
554 |        "      <td>...</td>\n",
555 |        "      <td>...</td>\n",
556 |        "      <td>...</td>\n",
557 |        "      <td>...</td>\n",
558 |        "      <td>...</td>\n",
559 |        "      <td>...</td>\n",
560 |        "      <td>...</td>\n",
561 |        "    </tr>\n",
562 |        "    <tr>\n",
563 |        "      <th>9535</th>\n",
564 |        "      <td>0</td>\n",
565 |        "      <td>0.610988</td>\n",
566 |        "      <td>4</td>\n",
567 |        "      <td>8.0</td>\n",
568 |        "      <td>0.543641</td>\n",
569 |        "      <td>0</td>\n",
570 |        "      <td>188.155738</td>\n",
571 |        "    </tr>\n",
572 |        "    <tr>\n",
573 |        "      <th>9536</th>\n",
574 |        "      <td>0</td>\n",
575 |        "      <td>0.746887</td>\n",
576 |        "      <td>3</td>\n",
577 |        "      <td>8.0</td>\n",
578 |        "      <td>0.549048</td>\n",
579 |        "      <td>0</td>\n",
580 |        "      <td>188.176164</td>\n",
581 |        "    </tr>\n",
582 |        "    <tr>\n",
583 |        "      <th>9537</th>\n",
584 |        "      <td>0</td>\n",
585 |        "      <td>0.557980</td>\n",
586 |        "      <td>3</td>\n",
587 |        "      <td>7.0</td>\n",
588 |        "      <td>0.705425</td>\n",
589 |        "      <td>0</td>\n",
590 |        "      <td>186.531008</td>\n",
591 |        "    </tr>\n",
592 |        "    <tr>\n",
593 |        "      <th>9538</th>\n",
594 |        "      <td>0</td>\n",
595 |        "      <td>0.584446</td>\n",
596 |        "      <td>4</td>\n",
597 |        "      <td>8.0</td>\n",
598 |        "      <td>0.607287</td>\n",
599 |        "      <td>1</td>\n",
600 |        "      <td>187.641370</td>\n",
601 |        "    </tr>\n",
602 |        "    <tr>\n",
603 |        "      <th>9539</th>\n",
604 |        "      <td>0</td>\n",
605 |        "      <td>0.626373</td>\n",
606 |        "      <td>3</td>\n",
607 |        "      <td>7.0</td>\n",
608 |        "      <td>0.706455</td>\n",
609 |        "      <td>1</td>\n",
610 |        "      <td>185.920934</td>\n",
611 |        "    </tr>\n",
612 |        "  </tbody>\n",
613 |        "</table>\n",
614 |        "<p>9540 rows × 7 columns</p>\n",
615 |        "</div>"
616 |       ],
617 |       "text/plain": [
618 |        "      promoted    review  projects  tenure  satisfaction  bonus  avg_hrs_month\n",
619 |        "0            0  0.577569         3     5.0      0.626759      0     180.866070\n",
620 |        "1            0  0.751900         3     6.0      0.443679      0     182.708149\n",
621 |        "2            0  0.722548         3     6.0      0.446823      0     184.416084\n",
622 |        "3            0  0.675158         4     8.0      0.440139      0     188.707545\n",
623 |        "4            0  0.676203         3     5.0      0.577607      1     179.821083\n",
624 |        "...        ...       ...       ...     ...           ...    ...            ...\n",
625 |        "9535         0  0.610988         4     8.0      0.543641      0     188.155738\n",
626 |        "9536         0  0.746887         3     8.0      0.549048      0     188.176164\n",
627 |        "9537         0  0.557980         3     7.0      0.705425      0     186.531008\n",
628 |        "9538         0  0.584446         4     8.0      0.607287      1     187.641370\n",
629 |        "9539         0  0.626373         3     7.0      0.706455      1     185.920934\n",
630 |        "\n",
631 |        "[9540 rows x 7 columns]"
632 |       ]
633 |      },
634 |      "execution_count": 4,
635 |      "metadata": {},
636 |      "output_type": "execute_result"
637 |     },
638 |     {
639 |      "name": "stdout",
640 |      "output_type": "stream",
641 |      "text": [
642 |       "time: 15.1 ms (started: 2023-03-26 23:09:33 +03:00)\n"
643 |      ]
644 |     }
645 |    ],
646 |    "source": [
647 |     "df.select_dtypes(exclude ='object')"
648 |    ]
649 |   },
650 |   {
651 |    "cell_type": "code",
652 |    "execution_count": null,
653 |    "id": "8ca95338",
654 |    "metadata": {},
655 |    "outputs": [],
656 |    "source": []
657 |   }
658 |  ],
659 |  "metadata": {
660 |   "kernelspec": {
661 |    "display_name": "Python 3 (ipykernel)",
662 |    "language": "python",
663 |    "name": "python3"
664 |   },
665 |   "language_info": {
666 |    "codemirror_mode": {
667 |     "name": "ipython",
668 |     "version": 3
669 |    },
670 |    "file_extension": ".py",
671 |    "mimetype": "text/x-python",
672 |    "name": "python",
673 |    "nbconvert_exporter": "python",
674 |    "pygments_lexer": "ipython3",
675 |    "version": "3.9.13"
676 |   }
677 |  },
678 |  "nbformat": 4,
679 |  "nbformat_minor": 5
680 | }
681 | 


--------------------------------------------------------------------------------
/Session4/swifter apply fastest run.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "73339d7b",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "From the documentation, it is stated that Swifter could apply function a hundred times faster than Pandas function. This, however, only applied if we are using a vectorized form of function."
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "markdown",
 13 |    "id": "ae1c4d99",
 14 |    "metadata": {},
 15 |    "source": [
 16 |     "https://github.com/jmcarpenter2/swifter/blob/master/docs/documentation.md\n",
 17 |     "\n",
 18 |     "https://github.com/jmcarpenter2/swifter"
 19 |    ]
 20 |   },
 21 |   {
 22 |    "cell_type": "code",
 23 |    "execution_count": 213,
 24 |    "id": "d59d4435",
 25 |    "metadata": {},
 26 |    "outputs": [
 27 |     {
 28 |      "name": "stdout",
 29 |      "output_type": "stream",
 30 |      "text": [
 31 |       "The autotime extension is already loaded. To reload it, use:\n",
 32 |       "  %reload_ext autotime\n"
 33 |      ]
 34 |     },
 35 |     {
 36 |      "data": {
 37 |       "text/html": [
 38 |        "<div>\n",
 39 |        "<style scoped>\n",
 40 |        "    .dataframe tbody tr th:only-of-type {\n",
 41 |        "        vertical-align: middle;\n",
 42 |        "    }\n",
 43 |        "\n",
 44 |        "    .dataframe tbody tr th {\n",
 45 |        "        vertical-align: top;\n",
 46 |        "    }\n",
 47 |        "\n",
 48 |        "    .dataframe thead th {\n",
 49 |        "        text-align: right;\n",
 50 |        "    }\n",
 51 |        "</style>\n",
 52 |        "<table border=\"1\" class=\"dataframe\">\n",
 53 |        "  <thead>\n",
 54 |        "    <tr style=\"text-align: right;\">\n",
 55 |        "      <th></th>\n",
 56 |        "      <th>department</th>\n",
 57 |        "      <th>promoted</th>\n",
 58 |        "      <th>review</th>\n",
 59 |        "      <th>projects</th>\n",
 60 |        "      <th>salary</th>\n",
 61 |        "      <th>tenure</th>\n",
 62 |        "      <th>satisfaction</th>\n",
 63 |        "      <th>bonus</th>\n",
 64 |        "      <th>avg_hrs_month</th>\n",
 65 |        "      <th>left</th>\n",
 66 |        "    </tr>\n",
 67 |        "  </thead>\n",
 68 |        "  <tbody>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>0</th>\n",
 71 |        "      <td>operations</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "      <td>0.577569</td>\n",
 74 |        "      <td>3</td>\n",
 75 |        "      <td>low</td>\n",
 76 |        "      <td>5.0</td>\n",
 77 |        "      <td>0.626759</td>\n",
 78 |        "      <td>0</td>\n",
 79 |        "      <td>180.866070</td>\n",
 80 |        "      <td>no</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>1</th>\n",
 84 |        "      <td>operations</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>0.751900</td>\n",
 87 |        "      <td>3</td>\n",
 88 |        "      <td>medium</td>\n",
 89 |        "      <td>6.0</td>\n",
 90 |        "      <td>0.443679</td>\n",
 91 |        "      <td>0</td>\n",
 92 |        "      <td>182.708149</td>\n",
 93 |        "      <td>no</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>2</th>\n",
 97 |        "      <td>support</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "      <td>0.722548</td>\n",
100 |        "      <td>3</td>\n",
101 |        "      <td>medium</td>\n",
102 |        "      <td>6.0</td>\n",
103 |        "      <td>0.446823</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>184.416084</td>\n",
106 |        "      <td>no</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>3</th>\n",
110 |        "      <td>logistics</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>0.675158</td>\n",
113 |        "      <td>4</td>\n",
114 |        "      <td>high</td>\n",
115 |        "      <td>8.0</td>\n",
116 |        "      <td>0.440139</td>\n",
117 |        "      <td>0</td>\n",
118 |        "      <td>188.707545</td>\n",
119 |        "      <td>no</td>\n",
120 |        "    </tr>\n",
121 |        "    <tr>\n",
122 |        "      <th>4</th>\n",
123 |        "      <td>sales</td>\n",
124 |        "      <td>0</td>\n",
125 |        "      <td>0.676203</td>\n",
126 |        "      <td>3</td>\n",
127 |        "      <td>high</td>\n",
128 |        "      <td>5.0</td>\n",
129 |        "      <td>0.577607</td>\n",
130 |        "      <td>1</td>\n",
131 |        "      <td>179.821083</td>\n",
132 |        "      <td>no</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>...</th>\n",
136 |        "      <td>...</td>\n",
137 |        "      <td>...</td>\n",
138 |        "      <td>...</td>\n",
139 |        "      <td>...</td>\n",
140 |        "      <td>...</td>\n",
141 |        "      <td>...</td>\n",
142 |        "      <td>...</td>\n",
143 |        "      <td>...</td>\n",
144 |        "      <td>...</td>\n",
145 |        "      <td>...</td>\n",
146 |        "    </tr>\n",
147 |        "    <tr>\n",
148 |        "      <th>9535</th>\n",
149 |        "      <td>operations</td>\n",
150 |        "      <td>0</td>\n",
151 |        "      <td>0.610988</td>\n",
152 |        "      <td>4</td>\n",
153 |        "      <td>medium</td>\n",
154 |        "      <td>8.0</td>\n",
155 |        "      <td>0.543641</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>188.155738</td>\n",
158 |        "      <td>yes</td>\n",
159 |        "    </tr>\n",
160 |        "    <tr>\n",
161 |        "      <th>9536</th>\n",
162 |        "      <td>logistics</td>\n",
163 |        "      <td>0</td>\n",
164 |        "      <td>0.746887</td>\n",
165 |        "      <td>3</td>\n",
166 |        "      <td>medium</td>\n",
167 |        "      <td>8.0</td>\n",
168 |        "      <td>0.549048</td>\n",
169 |        "      <td>0</td>\n",
170 |        "      <td>188.176164</td>\n",
171 |        "      <td>yes</td>\n",
172 |        "    </tr>\n",
173 |        "    <tr>\n",
174 |        "      <th>9537</th>\n",
175 |        "      <td>operations</td>\n",
176 |        "      <td>0</td>\n",
177 |        "      <td>0.557980</td>\n",
178 |        "      <td>3</td>\n",
179 |        "      <td>low</td>\n",
180 |        "      <td>7.0</td>\n",
181 |        "      <td>0.705425</td>\n",
182 |        "      <td>0</td>\n",
183 |        "      <td>186.531008</td>\n",
184 |        "      <td>yes</td>\n",
185 |        "    </tr>\n",
186 |        "    <tr>\n",
187 |        "      <th>9538</th>\n",
188 |        "      <td>IT</td>\n",
189 |        "      <td>0</td>\n",
190 |        "      <td>0.584446</td>\n",
191 |        "      <td>4</td>\n",
192 |        "      <td>medium</td>\n",
193 |        "      <td>8.0</td>\n",
194 |        "      <td>0.607287</td>\n",
195 |        "      <td>1</td>\n",
196 |        "      <td>187.641370</td>\n",
197 |        "      <td>yes</td>\n",
198 |        "    </tr>\n",
199 |        "    <tr>\n",
200 |        "      <th>9539</th>\n",
201 |        "      <td>finance</td>\n",
202 |        "      <td>0</td>\n",
203 |        "      <td>0.626373</td>\n",
204 |        "      <td>3</td>\n",
205 |        "      <td>low</td>\n",
206 |        "      <td>7.0</td>\n",
207 |        "      <td>0.706455</td>\n",
208 |        "      <td>1</td>\n",
209 |        "      <td>185.920934</td>\n",
210 |        "      <td>yes</td>\n",
211 |        "    </tr>\n",
212 |        "  </tbody>\n",
213 |        "</table>\n",
214 |        "<p>9540 rows × 10 columns</p>\n",
215 |        "</div>"
216 |       ],
217 |       "text/plain": [
218 |        "      department  promoted    review  projects  salary  tenure  satisfaction  \\\n",
219 |        "0     operations         0  0.577569         3     low     5.0      0.626759   \n",
220 |        "1     operations         0  0.751900         3  medium     6.0      0.443679   \n",
221 |        "2        support         0  0.722548         3  medium     6.0      0.446823   \n",
222 |        "3      logistics         0  0.675158         4    high     8.0      0.440139   \n",
223 |        "4          sales         0  0.676203         3    high     5.0      0.577607   \n",
224 |        "...          ...       ...       ...       ...     ...     ...           ...   \n",
225 |        "9535  operations         0  0.610988         4  medium     8.0      0.543641   \n",
226 |        "9536   logistics         0  0.746887         3  medium     8.0      0.549048   \n",
227 |        "9537  operations         0  0.557980         3     low     7.0      0.705425   \n",
228 |        "9538          IT         0  0.584446         4  medium     8.0      0.607287   \n",
229 |        "9539     finance         0  0.626373         3     low     7.0      0.706455   \n",
230 |        "\n",
231 |        "      bonus  avg_hrs_month left  \n",
232 |        "0         0     180.866070   no  \n",
233 |        "1         0     182.708149   no  \n",
234 |        "2         0     184.416084   no  \n",
235 |        "3         0     188.707545   no  \n",
236 |        "4         1     179.821083   no  \n",
237 |        "...     ...            ...  ...  \n",
238 |        "9535      0     188.155738  yes  \n",
239 |        "9536      0     188.176164  yes  \n",
240 |        "9537      0     186.531008  yes  \n",
241 |        "9538      1     187.641370  yes  \n",
242 |        "9539      1     185.920934  yes  \n",
243 |        "\n",
244 |        "[9540 rows x 10 columns]"
245 |       ]
246 |      },
247 |      "execution_count": 213,
248 |      "metadata": {},
249 |      "output_type": "execute_result"
250 |     },
251 |     {
252 |      "name": "stdout",
253 |      "output_type": "stream",
254 |      "text": [
255 |       "time: 31 ms (started: 2023-03-27 04:14:03 +03:00)\n"
256 |      ]
257 |     }
258 |    ],
259 |    "source": [
260 |     "import warnings\n",
261 |     "warnings.filterwarnings(\"ignore\")\n",
262 |     "import pandas as pd\n",
263 |     "import numpy as np\n",
264 |     "import swifter\n",
265 |     "import autotime\n",
266 |     "%load_ext autotime\n",
267 |     "df=pd.read_csv(\"employee_churn_data.csv\")\n",
268 |     "df"
269 |    ]
270 |   },
271 |   {
272 |    "cell_type": "code",
273 |    "execution_count": 204,
274 |    "id": "848016dc",
275 |    "metadata": {},
276 |    "outputs": [
277 |     {
278 |      "name": "stdout",
279 |      "output_type": "stream",
280 |      "text": [
281 |       "time: 1.17 ms (started: 2023-03-27 03:32:40 +03:00)\n"
282 |      ]
283 |     }
284 |    ],
285 |    "source": [
286 |     "df=df.select_dtypes(include=['int64',\"float64\"])"
287 |    ]
288 |   },
289 |   {
290 |    "cell_type": "code",
291 |    "execution_count": 205,
292 |    "id": "b580ffb6",
293 |    "metadata": {},
294 |    "outputs": [
295 |     {
296 |      "name": "stdout",
297 |      "output_type": "stream",
298 |      "text": [
299 |       "time: 64.9 ms (started: 2023-03-27 03:32:40 +03:00)\n"
300 |      ]
301 |     }
302 |    ],
303 |    "source": [
304 |     "for i in range(6):\n",
305 |     "    df=df.append(df)"
306 |    ]
307 |   },
308 |   {
309 |    "cell_type": "code",
310 |    "execution_count": 212,
311 |    "id": "bbb5bde1",
312 |    "metadata": {},
313 |    "outputs": [
314 |     {
315 |      "data": {
316 |       "text/plain": [
317 |        "610560"
318 |       ]
319 |      },
320 |      "execution_count": 212,
321 |      "metadata": {},
322 |      "output_type": "execute_result"
323 |     },
324 |     {
325 |      "name": "stdout",
326 |      "output_type": "stream",
327 |      "text": [
328 |       "time: 3.71 ms (started: 2023-03-27 03:33:12 +03:00)\n"
329 |      ]
330 |     }
331 |    ],
332 |    "source": [
333 |     "df.shape[0]"
334 |    ]
335 |   },
336 |   {
337 |    "cell_type": "code",
338 |    "execution_count": 206,
339 |    "id": "6a0fd71e",
340 |    "metadata": {},
341 |    "outputs": [
342 |     {
343 |      "name": "stdout",
344 |      "output_type": "stream",
345 |      "text": [
346 |       "time: 115 ms (started: 2023-03-27 03:32:40 +03:00)\n"
347 |      ]
348 |     }
349 |    ],
350 |    "source": [
351 |     "a = df.apply(lambda x: x/2 -1)"
352 |    ]
353 |   },
354 |   {
355 |    "cell_type": "code",
356 |    "execution_count": 207,
357 |    "id": "8868d15e",
358 |    "metadata": {},
359 |    "outputs": [
360 |     {
361 |      "name": "stdout",
362 |      "output_type": "stream",
363 |      "text": [
364 |       "time: 165 ms (started: 2023-03-27 03:32:40 +03:00)\n"
365 |      ]
366 |     }
367 |    ],
368 |    "source": [
369 |     "b = df.swifter.apply(lambda x: x/2 -1)"
370 |    ]
371 |   },
372 |   {
373 |    "cell_type": "code",
374 |    "execution_count": 208,
375 |    "id": "72e2953a",
376 |    "metadata": {},
377 |    "outputs": [
378 |     {
379 |      "name": "stdout",
380 |      "output_type": "stream",
381 |      "text": [
382 |       "time: 6.84 s (started: 2023-03-27 03:32:40 +03:00)\n"
383 |      ]
384 |     }
385 |    ],
386 |    "source": [
387 |     "def scoring_comment(x):\n",
388 |     "    if x['bonus'] == 0:\n",
389 |     "        return x['review'] *2\n",
390 |     "    else:\n",
391 |     "        return x['review']\n",
392 |     "#Trying applying the function using Pandas apply\n",
393 |     "\n",
394 |     "a = df.apply(scoring_comment, axis =1)"
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "code",
399 |    "execution_count": 209,
400 |    "id": "e9e03a26",
401 |    "metadata": {},
402 |    "outputs": [
403 |     {
404 |      "data": {
405 |       "application/vnd.jupyter.widget-view+json": {
406 |        "model_id": "e9f976687ee641bd8a43e354108a0f3d",
407 |        "version_major": 2,
408 |        "version_minor": 0
409 |       },
410 |       "text/plain": [
411 |        "Pandas Apply:   0%|          | 0/610560 [00:00<?, ?it/s]"
412 |       ]
413 |      },
414 |      "metadata": {},
415 |      "output_type": "display_data"
416 |     },
417 |     {
418 |      "name": "stdout",
419 |      "output_type": "stream",
420 |      "text": [
421 |       "time: 9.96 s (started: 2023-03-27 03:32:47 +03:00)\n"
422 |      ]
423 |     }
424 |    ],
425 |    "source": [
426 |     "\n",
427 |     "b = df.swifter.apply(scoring_comment, axis =1)"
428 |    ]
429 |   },
430 |   {
431 |    "cell_type": "code",
432 |    "execution_count": 210,
433 |    "id": "748ece0d",
434 |    "metadata": {},
435 |    "outputs": [
436 |     {
437 |      "name": "stdout",
438 |      "output_type": "stream",
439 |      "text": [
440 |       "time: 12.8 s (started: 2023-03-27 03:32:57 +03:00)\n"
441 |      ]
442 |     }
443 |    ],
444 |    "source": [
445 |     "def scoring_comment_vectorized(x):\n",
446 |     "    return np.where(x['bonus'] ==0, x['review']*2, x['review'])\n",
447 |     "\n",
448 |     "a = df.apply(scoring_comment_vectorized, axis =1)"
449 |    ]
450 |   },
451 |   {
452 |    "cell_type": "code",
453 |    "execution_count": 211,
454 |    "id": "500bc1f4",
455 |    "metadata": {},
456 |    "outputs": [
457 |     {
458 |      "name": "stdout",
459 |      "output_type": "stream",
460 |      "text": [
461 |       "time: 34.1 ms (started: 2023-03-27 03:33:10 +03:00)\n"
462 |      ]
463 |     }
464 |    ],
465 |    "source": [
466 |     "b = df.swifter.apply(scoring_comment_vectorized, axis =1)"
467 |    ]
468 |   },
469 |   {
470 |    "cell_type": "markdown",
471 |    "id": "e7ce1ddb",
472 |    "metadata": {},
473 |    "source": [
474 |     "https://morioh.com/p/26c8b6f1a4a1"
475 |    ]
476 |   },
477 |   {
478 |    "cell_type": "code",
479 |    "execution_count": null,
480 |    "id": "86e8afe8",
481 |    "metadata": {},
482 |    "outputs": [],
483 |    "source": []
484 |   }
485 |  ],
486 |  "metadata": {
487 |   "kernelspec": {
488 |    "display_name": "Python 3 (ipykernel)",
489 |    "language": "python",
490 |    "name": "python3"
491 |   },
492 |   "language_info": {
493 |    "codemirror_mode": {
494 |     "name": "ipython",
495 |     "version": 3
496 |    },
497 |    "file_extension": ".py",
498 |    "mimetype": "text/x-python",
499 |    "name": "python",
500 |    "nbconvert_exporter": "python",
501 |    "pygments_lexer": "ipython3",
502 |    "version": "3.9.13"
503 |   }
504 |  },
505 |  "nbformat": 4,
506 |  "nbformat_minor": 5
507 | }
508 | 


--------------------------------------------------------------------------------
/Session5/pd.to_numeric errors coerce.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 13,
  6 |    "id": "2ad201ba",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "text/html": [
 12 |        "<div>\n",
 13 |        "<style scoped>\n",
 14 |        "    .dataframe tbody tr th:only-of-type {\n",
 15 |        "        vertical-align: middle;\n",
 16 |        "    }\n",
 17 |        "\n",
 18 |        "    .dataframe tbody tr th {\n",
 19 |        "        vertical-align: top;\n",
 20 |        "    }\n",
 21 |        "\n",
 22 |        "    .dataframe thead th {\n",
 23 |        "        text-align: right;\n",
 24 |        "    }\n",
 25 |        "</style>\n",
 26 |        "<table border=\"1\" class=\"dataframe\">\n",
 27 |        "  <thead>\n",
 28 |        "    <tr style=\"text-align: right;\">\n",
 29 |        "      <th></th>\n",
 30 |        "      <th>set_of_numbers</th>\n",
 31 |        "    </tr>\n",
 32 |        "  </thead>\n",
 33 |        "  <tbody>\n",
 34 |        "    <tr>\n",
 35 |        "      <th>0</th>\n",
 36 |        "      <td>NaN</td>\n",
 37 |        "    </tr>\n",
 38 |        "    <tr>\n",
 39 |        "      <th>1</th>\n",
 40 |        "      <td>6.4</td>\n",
 41 |        "    </tr>\n",
 42 |        "    <tr>\n",
 43 |        "      <th>2</th>\n",
 44 |        "      <td>70.2</td>\n",
 45 |        "    </tr>\n",
 46 |        "    <tr>\n",
 47 |        "      <th>3</th>\n",
 48 |        "      <td>NaN</td>\n",
 49 |        "    </tr>\n",
 50 |        "    <tr>\n",
 51 |        "      <th>4</th>\n",
 52 |        "      <td>NaN</td>\n",
 53 |        "    </tr>\n",
 54 |        "    <tr>\n",
 55 |        "      <th>5</th>\n",
 56 |        "      <td>8</td>\n",
 57 |        "    </tr>\n",
 58 |        "    <tr>\n",
 59 |        "      <th>6</th>\n",
 60 |        "      <td>9</td>\n",
 61 |        "    </tr>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>7</th>\n",
 64 |        "      <td>10</td>\n",
 65 |        "    </tr>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>8</th>\n",
 68 |        "      <td>NaN</td>\n",
 69 |        "    </tr>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>9</th>\n",
 72 |        "      <td>-</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>10</th>\n",
 76 |        "      <td>*</td>\n",
 77 |        "    </tr>\n",
 78 |        "  </tbody>\n",
 79 |        "</table>\n",
 80 |        "</div>"
 81 |       ],
 82 |       "text/plain": [
 83 |        "   set_of_numbers\n",
 84 |        "0             NaN\n",
 85 |        "1             6.4\n",
 86 |        "2            70.2\n",
 87 |        "3             NaN\n",
 88 |        "4             NaN\n",
 89 |        "5               8\n",
 90 |        "6               9\n",
 91 |        "7              10\n",
 92 |        "8             NaN\n",
 93 |        "9               -\n",
 94 |        "10              *"
 95 |       ]
 96 |      },
 97 |      "execution_count": 13,
 98 |      "metadata": {},
 99 |      "output_type": "execute_result"
100 |     }
101 |    ],
102 |    "source": [
103 |     "import pandas as pd \n",
104 |     "import numpy as np\n",
105 |     "import pandas as pd\n",
106 |     "import numpy as np\n",
107 |     "\n",
108 |     "data = {'set_of_numbers': [np.nan,6.4,70.2,np.nan,np.nan,8,9,10,np.nan,\"-\",\"*\"]}\n",
109 |     "df = pd.DataFrame(data)\n",
110 |     "\n",
111 |     "df"
112 |    ]
113 |   },
114 |   {
115 |    "cell_type": "code",
116 |    "execution_count": 14,
117 |    "id": "195b4bb6",
118 |    "metadata": {},
119 |    "outputs": [
120 |     {
121 |      "data": {
122 |       "text/plain": [
123 |        "0      NaN\n",
124 |        "1      6.4\n",
125 |        "2     70.2\n",
126 |        "3      NaN\n",
127 |        "4      NaN\n",
128 |        "5        8\n",
129 |        "6        9\n",
130 |        "7       10\n",
131 |        "8      NaN\n",
132 |        "9        -\n",
133 |        "10       *\n",
134 |        "Name: set_of_numbers, dtype: object"
135 |       ]
136 |      },
137 |      "execution_count": 14,
138 |      "metadata": {},
139 |      "output_type": "execute_result"
140 |     }
141 |    ],
142 |    "source": [
143 |     "pd.to_numeric(df[\"set_of_numbers\"],errors ='ignore')"
144 |    ]
145 |   },
146 |   {
147 |    "cell_type": "code",
148 |    "execution_count": 15,
149 |    "id": "700569a2",
150 |    "metadata": {},
151 |    "outputs": [
152 |     {
153 |      "data": {
154 |       "text/plain": [
155 |        "0      NaN\n",
156 |        "1      6.4\n",
157 |        "2     70.2\n",
158 |        "3      NaN\n",
159 |        "4      NaN\n",
160 |        "5      8.0\n",
161 |        "6      9.0\n",
162 |        "7     10.0\n",
163 |        "8      NaN\n",
164 |        "9      NaN\n",
165 |        "10     NaN\n",
166 |        "Name: set_of_numbers, dtype: float64"
167 |       ]
168 |      },
169 |      "execution_count": 15,
170 |      "metadata": {},
171 |      "output_type": "execute_result"
172 |     }
173 |    ],
174 |    "source": [
175 |     "pd.to_numeric(df[\"set_of_numbers\"], errors ='coerce')"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "code",
180 |    "execution_count": 16,
181 |    "id": "62e91dca",
182 |    "metadata": {},
183 |    "outputs": [
184 |     {
185 |      "data": {
186 |       "text/plain": [
187 |        "0    10\n",
188 |        "1    12\n",
189 |        "2    15\n",
190 |        "3    20\n",
191 |        "4     A\n",
192 |        "5    31\n",
193 |        "6     C\n",
194 |        "7     D\n",
195 |        "dtype: object"
196 |       ]
197 |      },
198 |      "execution_count": 16,
199 |      "metadata": {},
200 |      "output_type": "execute_result"
201 |     }
202 |    ],
203 |    "source": [
204 |     "df = pd.Series(['10', '12', '15', '20', 'A', '31', 'C', 'D'])\n",
205 |     "df"
206 |    ]
207 |   },
208 |   {
209 |    "cell_type": "code",
210 |    "execution_count": 18,
211 |    "id": "807da86c",
212 |    "metadata": {},
213 |    "outputs": [
214 |     {
215 |      "data": {
216 |       "text/plain": [
217 |        "0    10.0\n",
218 |        "1    12.0\n",
219 |        "2    15.0\n",
220 |        "3    20.0\n",
221 |        "4     NaN\n",
222 |        "5    31.0\n",
223 |        "6     NaN\n",
224 |        "7     NaN\n",
225 |        "dtype: float64"
226 |       ]
227 |      },
228 |      "execution_count": 18,
229 |      "metadata": {},
230 |      "output_type": "execute_result"
231 |     }
232 |    ],
233 |    "source": [
234 |     "pd.to_numeric(df, errors='coerce')"
235 |    ]
236 |   },
237 |   {
238 |    "cell_type": "code",
239 |    "execution_count": null,
240 |    "id": "4bfdd542",
241 |    "metadata": {},
242 |    "outputs": [],
243 |    "source": []
244 |   }
245 |  ],
246 |  "metadata": {
247 |   "kernelspec": {
248 |    "display_name": "Python 3 (ipykernel)",
249 |    "language": "python",
250 |    "name": "python3"
251 |   },
252 |   "language_info": {
253 |    "codemirror_mode": {
254 |     "name": "ipython",
255 |     "version": 3
256 |    },
257 |    "file_extension": ".py",
258 |    "mimetype": "text/x-python",
259 |    "name": "python",
260 |    "nbconvert_exporter": "python",
261 |    "pygments_lexer": "ipython3",
262 |    "version": "3.9.13"
263 |   }
264 |  },
265 |  "nbformat": 4,
266 |  "nbformat_minor": 5
267 | }
268 | 


--------------------------------------------------------------------------------