\n",
"
pandas.plotting._core.hist_series
def hist_series(by=None, ax=None, grid: bool=True, xlabelsize: int | None=None, xrot: float | None=None, ylabelsize: int | None=None, yrot: float | None=None, figsize: tuple[int, int] | None=None, bins: int | Sequence[int]=10, backend: str | None=None, legend: bool=False, **kwargs)
/usr/local/lib/python3.12/dist-packages/pandas/plotting/_core.pyDraw histogram of the input series using matplotlib.\n",
"\n",
"Parameters\n",
"----------\n",
"by : object, optional\n",
" If passed, then used to form histograms for separate groups.\n",
"ax : matplotlib axis object\n",
" If not passed, uses gca().\n",
"grid : bool, default True\n",
" Whether to show axis grid lines.\n",
"xlabelsize : int, default None\n",
" If specified changes the x-axis label size.\n",
"xrot : float, default None\n",
" Rotation of x axis labels.\n",
"ylabelsize : int, default None\n",
" If specified changes the y-axis label size.\n",
"yrot : float, default None\n",
" Rotation of y axis labels.\n",
"figsize : tuple, default None\n",
" Figure size in inches by default.\n",
"bins : int or sequence, default 10\n",
" Number of histogram bins to be used. If an integer is given, bins + 1\n",
" bin edges are calculated and returned. If bins is a sequence, gives\n",
" bin edges, including left edge of first bin and right edge of last\n",
" bin. In this case, bins is returned unmodified.\n",
"backend : str, default None\n",
" Backend to use instead of the backend specified in the option\n",
" ``plotting.backend``. For instance, 'matplotlib'. Alternatively, to\n",
" specify the ``plotting.backend`` for the whole session, set\n",
" ``pd.options.plotting.backend``.\n",
"legend : bool, default False\n",
" Whether to show the legend.\n",
"\n",
"**kwargs\n",
" To be passed to the actual plotting function.\n",
"\n",
"Returns\n",
"-------\n",
"matplotlib.AxesSubplot\n",
" A histogram plot.\n",
"\n",
"See Also\n",
"--------\n",
"matplotlib.axes.Axes.hist : Plot a histogram using matplotlib.\n",
"\n",
"Examples\n",
"--------\n",
"For Series:\n",
"\n",
".. plot::\n",
" :context: close-figs\n",
"\n",
" >>> lst = ['a', 'a', 'a', 'b', 'b', 'b']\n",
" >>> ser = pd.Series([1, 2, 2, 4, 6, 6], index=lst)\n",
" >>> hist = ser.hist()\n",
"\n",
"For Groupby:\n",
"\n",
".. plot::\n",
" :context: close-figs\n",
"\n",
" >>> lst = ['a', 'a', 'a', 'b', 'b', 'b']\n",
" >>> ser = pd.Series([1, 2, 2, 4, 6, 6], index=lst)\n",
" >>> hist = ser.groupby(level=0).hist()\n",
" \n",
"
"
]
},
"metadata": {},
"execution_count": 22
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "2e41caaf"
},
"source": [
"# Convert labels to numerical format\n",
"df['labels'] = df['labels'].map({'ham': 0, 'spam': 1})"
],
"execution_count": 23,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "c841b673"
},
"source": [
"# Split the data into training and testing sets\n",
"X_train, X_test, y_train, y_test = train_test_split(df['data'], df['labels'], test_size=0.33, random_state=42)"
],
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "412cf5a6"
},
"source": [
"# Vectorize the text data using TF-IDF\n",
"vectorizer = TfidfVectorizer(decode_error='ignore')\n",
"X_train_vectorized = vectorizer.fit_transform(X_train)\n",
"X_test_vectorized = vectorizer.transform(X_test)"
],
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"source": [
"X_train"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 458
},
"id": "RPOkw_7TPuiD",
"outputId": "a879716e-2b7d-4bcd-d001-ceac04e028af"
},
"execution_count": 25,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"3235 Aight text me when you're back at mu and I'll ...\n",
"945 I cant wait to see you! How were the photos we...\n",
"5319 Kothi print out marandratha.\n",
"5528 Its just the effect of irritation. Just ignore it\n",
"247 Kallis wont bat in 2nd innings.\n",
" ... \n",
"3772 I came hostel. I m going to sleep. Plz call me...\n",
"5191 Sorry, I'll call later\n",
"5226 Prabha..i'm soryda..realy..frm heart i'm sory\n",
"5390 Nt joking seriously i told\n",
"860 In work now. Going have in few min.\n",
"Name: data, Length: 3733, dtype: object"
],
"text/html": [
"