{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "lamda.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyMOyD+4tvDOYCdm1AxRsxK1",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
" "
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "W6rzI8z8wH43"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import nltk\n",
"nltk.download('stopwords')\n",
"\n",
"import pandas as pd\n",
"import re\n",
"import string\n",
"pd.set_option('display.max_colwidth', 200)\n",
"\n",
"stopwords = nltk.corpus.stopwords.words('english')\n",
"\n",
"data = pd.DataFrame({\n",
" 'label' : [ 'one', 'second'],\n",
" 'body_text' : [ 'The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit.', \\\n",
" 'It wants voters to remember the nonstop chaos of his administration, his Twitter rants, \\\n",
" how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election results.']\n",
"})\n",
"data"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 208
},
"id": "EYAVniDWwH0r",
"outputId": "cd18dd2d-9720-40de-f8b9-2137b99c70d0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
" label \\\n",
"0 one \n",
"1 second \n",
"\n",
" body_text \n",
"0 The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
"1 It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... "
],
"text/html": [
"\n",
"
\n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" label \n",
" body_text \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" one \n",
" The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
" \n",
" \n",
" 1 \n",
" second \n",
" It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 7
}
]
},
{
"cell_type": "code",
"source": [
"def clean_text(text):\n",
" text = \"\".join([word for word in text if word not in string.punctuation])\n",
" tokens = re.split('\\W+', text)\n",
" text = [word for word in tokens if word not in stopwords]\n",
" return text\n",
"\n",
"data['body_text_nostop'] = data['body_text'].apply(lambda x: clean_text(x.lower()))\n",
"\n",
"data.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 208
},
"id": "kCVV5Vk4wHxk",
"outputId": "a03da592-c3c2-4aed-c741-8d1c527d461a"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" label \\\n",
"0 one \n",
"1 second \n",
"\n",
" body_text \\\n",
"0 The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
"1 It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... \n",
"\n",
" body_text_nostop \n",
"0 [democratic, party, complicated, relationship, donald, trump, likes, admit] \n",
"1 [wants, voters, remember, nonstop, chaos, administration, twitter, rants, debased, presidency, jan, 6, stop, lying, 2020, election, results] "
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" label \n",
" body_text \n",
" body_text_nostop \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" one \n",
" The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
" [democratic, party, complicated, relationship, donald, trump, likes, admit] \n",
" \n",
" \n",
" 1 \n",
" second \n",
" It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... \n",
" [wants, voters, remember, nonstop, chaos, administration, twitter, rants, debased, presidency, jan, 6, stop, lying, 2020, election, results] \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"source": [
"ps = nltk.PorterStemmer()\n",
"\n",
"# stem is one of attribute or function of PorterStemmer of NLTK\n",
"def stemming(tokenized_text):\n",
" text = [ps.stem(word) for word in tokenized_text]\n",
" return text\n",
"\n",
"data['body_text_stemmed'] = data['body_text_nostop'].apply(lambda x: stemming(x))\n",
"\n",
"data.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 226
},
"id": "RvUyDVsjwHub",
"outputId": "6826f2d2-1028-47b3-e72c-00f3254c789e"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" label \\\n",
"0 one \n",
"1 second \n",
"\n",
" body_text \\\n",
"0 The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
"1 It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... \n",
"\n",
" body_text_nostop \\\n",
"0 [democratic, party, complicated, relationship, donald, trump, likes, admit] \n",
"1 [wants, voters, remember, nonstop, chaos, administration, twitter, rants, debased, presidency, jan, 6, stop, lying, 2020, election, results] \n",
"\n",
" body_text_stemmed \n",
"0 [democrat, parti, complic, relationship, donald, trump, like, admit] \n",
"1 [want, voter, rememb, nonstop, chao, administr, twitter, rant, debas, presid, jan, 6, stop, lie, 2020, elect, result] "
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" label \n",
" body_text \n",
" body_text_nostop \n",
" body_text_stemmed \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" one \n",
" The Democratic Party has a more complicated relationship with Donald Trump than it likes to admit. \n",
" [democratic, party, complicated, relationship, donald, trump, likes, admit] \n",
" [democrat, parti, complic, relationship, donald, trump, like, admit] \n",
" \n",
" \n",
" 1 \n",
" second \n",
" It wants voters to remember the nonstop chaos of his administration, his Twitter rants, how he debased the presidency on Jan. 6 and won’t stop lying about the 2020 election res... \n",
" [wants, voters, remember, nonstop, chaos, administration, twitter, rants, debased, presidency, jan, 6, stop, lying, 2020, election, results] \n",
" [want, voter, rememb, nonstop, chao, administr, twitter, rant, debas, presid, jan, 6, stop, lie, 2020, elect, result] \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 10
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "o4c1_C6IwHo9"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bx1rb2bR43Ep",
"outputId": "cd3920f6-3f3d-4dd9-f03b-17ed32338982"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"15\n"
]
}
],
"source": [
"x = lambda a : a + 10\n",
"print(x(5))"
]
},
{
"cell_type": "code",
"source": [
"y=lambda x: x+3\n",
"y(5)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ZiHuYN6E95eM",
"outputId": "fd5adf97-9f18-4dfe-e5b1-9a84ce3b57ba"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"8"
]
},
"metadata": {},
"execution_count": 100
}
]
},
{
"cell_type": "code",
"source": [
"(lambda x: x+3)(5)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cpuZg-s4gtjQ",
"outputId": "194d9300-c969-4e36-f517-01ce7bf5a31d"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"8"
]
},
"metadata": {},
"execution_count": 102
}
]
},
{
"cell_type": "code",
"source": [
"def add(x):\n",
" return x+3\n",
"\n",
"add(5)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "F9amlr6Z95hw",
"outputId": "121a289b-8475-4df8-a356-f0a1c8238310"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"8"
]
},
"metadata": {},
"execution_count": 103
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "M6ID7Ag3BNMo"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"dff=pd.DataFrame([[1, 2, 3, 4],\n",
" [5, 6, 7, 8],\n",
" [np.square(6), np.sqrt(144), 22, 34]])\n",
"\n",
"dff.index=[0,1,2]\n",
"dff.columns=['A', 'B', 'C','D']\n",
"\n",
"dff"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "D07j5IEoFiF1",
"outputId": "a95a0984-eb93-4b32-b360-dbfee5db5eaf"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 1 2.0 3 4\n",
"1 5 6.0 7 8\n",
"2 36 12.0 22 34"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 1 \n",
" 2.0 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 5 \n",
" 6.0 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 36 \n",
" 12.0 \n",
" 22 \n",
" 34 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"df=pd.DataFrame([[1, 2, 3, 4],\n",
" [5, 6, 7, 8],\n",
" [9, 10, 11, 12]],\n",
" index=[0,1,2],\n",
" columns=['A', 'B', 'C','D'])\n",
"\n",
"df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "40nKkQcPBNHT",
"outputId": "842a0669-611f-4ec6-b6c6-66d42123ede3"
},
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 1 2 3 4\n",
"1 5 6 7 8\n",
"2 9 10 11 12"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 1 \n",
" 2 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 5 \n",
" 6 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 9 \n",
" 10 \n",
" 11 \n",
" 12 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"source": [
"df2 = df.apply(lambda x : x + 10)\n",
"print(df2)\n",
"df3 = df + 10\n",
"print(df3)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "u84odJwIElIq",
"outputId": "763dd972-c693-4794-f804-b6fcfd620d03"
},
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" A B C D\n",
"0 11 12 13 14\n",
"1 15 16 17 18\n",
"2 19 20 21 22\n",
" A B C D\n",
"0 11 12 13 14\n",
"1 15 16 17 18\n",
"2 19 20 21 22\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"df.at[1, 'A'] =np.square(df.at[1, 'A'])\n",
"df.at[0, 'A'] = 20\n",
"\n",
"df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "936Lyb9LJtp3",
"outputId": "5c0e3b63-d8e2-46eb-f2b7-5ba88a0022c1"
},
"execution_count": 10,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 20 2 3 4\n",
"1 25 6 7 8\n",
"2 9 10 11 12"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 20 \n",
" 2 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 25 \n",
" 6 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 9 \n",
" 10 \n",
" 11 \n",
" 12 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 10
}
]
},
{
"cell_type": "code",
"source": [
"df2[\"A\"] = df2[\"A\"].apply(lambda x: x-2)\n",
"df2"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "JEt_HqZ7FCfr",
"outputId": "d5f69c28-ba3a-4357-98c4-7bc706015d1d"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 9 12 13 14\n",
"1 13 16 17 18\n",
"2 17 30 32 44"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 9 \n",
" 12 \n",
" 13 \n",
" 14 \n",
" \n",
" \n",
" 1 \n",
" 13 \n",
" 16 \n",
" 17 \n",
" 18 \n",
" \n",
" \n",
" 2 \n",
" 17 \n",
" 30 \n",
" 32 \n",
" 44 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 77
}
]
},
{
"cell_type": "code",
"source": [
"df2 = df.apply(lambda x: np.square(x) if x.name in ['A','B'] else x)\n",
"df2"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "VgE-eqtpFWIB",
"outputId": "5ee5e765-9efa-4b81-a7d9-51890a85e4d4"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 400 4 3 4\n",
"1 625 36 7 8\n",
"2 81 400 22 34"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 400 \n",
" 4 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 625 \n",
" 36 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 81 \n",
" 400 \n",
" 22 \n",
" 34 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 78
}
]
},
{
"cell_type": "code",
"source": [
"# Using DataFrame.map() to Single Column\n",
"df['A'] = df['A'].map(lambda A: A/2.)\n",
"df\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "HQRurBUC95ug",
"outputId": "a6497f96-0dfa-494f-a1a3-2b661718b7e7"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 10.0 2 3 4\n",
"1 12.5 6 7 8\n",
"2 4.5 20 22 34"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 10.0 \n",
" 2 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 12.5 \n",
" 6 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 4.5 \n",
" 20 \n",
" 22 \n",
" 34 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 79
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "Z_hrLX7tMYzU"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Using DataFrame.assign() and Lambda\n",
"df2 = df.assign(B=lambda df: df.B/2)\n",
"df2"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 143
},
"id": "Z1pDlYPO95xL",
"outputId": "02fc7b24-666d-4bb4-bce6-d59f62a1fb83"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" A B C D\n",
"0 10.0 1.0 3 4\n",
"1 12.5 3.0 7 8\n",
"2 4.5 10.0 22 34"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" A \n",
" B \n",
" C \n",
" D \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 10.0 \n",
" 1.0 \n",
" 3 \n",
" 4 \n",
" \n",
" \n",
" 1 \n",
" 12.5 \n",
" 3.0 \n",
" 7 \n",
" 8 \n",
" \n",
" \n",
" 2 \n",
" 4.5 \n",
" 10.0 \n",
" 22 \n",
" 34 \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 81
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "lY83XOwQ95z5"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# importing pandas and numpy\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# crete a sample dataframe\n",
"data = pd.DataFrame({\n",
" 'age' : [ 10, 22, 13, 21, 12, 11, 17],\n",
" 'section' : [ 'A', 'B', 'C', 'B', 'B', 'A', 'A'],\n",
" 'city' : [ 'Gurgaon', 'Delhi', 'Mumbai', 'Delhi', 'Mumbai', 'Delhi', 'Mumbai'],\n",
" 'gender' : [ 'M', 'F', 'F', 'M', 'M', 'M', 'F'],\n",
" 'favourite_color' : [ 'red', np.NAN, 'yellow', np.NAN, 'black', 'green', 'red']\n",
"})\n",
"\n",
"# view the data\n",
"data"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 269
},
"id": "GteCCb_f952t",
"outputId": "7a9af371-5e31-4fd6-bafa-2fe9f6492cd1"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" age section city gender favourite_color\n",
"0 10 A Gurgaon M red\n",
"1 22 B Delhi F NaN\n",
"2 13 C Mumbai F yellow\n",
"3 21 B Delhi M NaN\n",
"4 12 B Mumbai M black\n",
"5 11 A Delhi M green\n",
"6 17 A Mumbai F red"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" age \n",
" section \n",
" city \n",
" gender \n",
" favourite_color \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 10 \n",
" A \n",
" Gurgaon \n",
" M \n",
" red \n",
" \n",
" \n",
" 1 \n",
" 22 \n",
" B \n",
" Delhi \n",
" F \n",
" NaN \n",
" \n",
" \n",
" 2 \n",
" 13 \n",
" C \n",
" Mumbai \n",
" F \n",
" yellow \n",
" \n",
" \n",
" 3 \n",
" 21 \n",
" B \n",
" Delhi \n",
" M \n",
" NaN \n",
" \n",
" \n",
" 4 \n",
" 12 \n",
" B \n",
" Mumbai \n",
" M \n",
" black \n",
" \n",
" \n",
" 5 \n",
" 11 \n",
" A \n",
" Delhi \n",
" M \n",
" green \n",
" \n",
" \n",
" 6 \n",
" 17 \n",
" A \n",
" Mumbai \n",
" F \n",
" red \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 88
}
]
},
{
"cell_type": "code",
"source": [
"len(data)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Fqs3VPr7Nhuc",
"outputId": "1e4acc99-d15b-47b3-8ea9-1849a4f53727"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"7"
]
},
"metadata": {},
"execution_count": 91
}
]
},
{
"cell_type": "code",
"source": [
"for i in range(len(data)):\n",
" data.at[i, 'age']= i * 10\n",
"\n",
"data"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 269
},
"id": "hM2d889P955Z",
"outputId": "183d4863-8eaf-4023-d77f-22d0396ef3fb"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" age section city gender favourite_color\n",
"0 0 A Gurgaon M red\n",
"1 10 B Delhi F NaN\n",
"2 20 C Mumbai F yellow\n",
"3 30 B Delhi M NaN\n",
"4 40 B Mumbai M black\n",
"5 50 A Delhi M green\n",
"6 60 A Mumbai F red"
],
"text/html": [
"\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" age \n",
" section \n",
" city \n",
" gender \n",
" favourite_color \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 0 \n",
" A \n",
" Gurgaon \n",
" M \n",
" red \n",
" \n",
" \n",
" 1 \n",
" 10 \n",
" B \n",
" Delhi \n",
" F \n",
" NaN \n",
" \n",
" \n",
" 2 \n",
" 20 \n",
" C \n",
" Mumbai \n",
" F \n",
" yellow \n",
" \n",
" \n",
" 3 \n",
" 30 \n",
" B \n",
" Delhi \n",
" M \n",
" NaN \n",
" \n",
" \n",
" 4 \n",
" 40 \n",
" B \n",
" Mumbai \n",
" M \n",
" black \n",
" \n",
" \n",
" 5 \n",
" 50 \n",
" A \n",
" Delhi \n",
" M \n",
" green \n",
" \n",
" \n",
" 6 \n",
" 60 \n",
" A \n",
" Mumbai \n",
" F \n",
" red \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
" \n",
"
\n",
"
\n",
" "
]
},
"metadata": {},
"execution_count": 90
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "YVZQZvsB958z"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "KnjMvwQA96Bd"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "VeLqOt8l96Em"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"x = lambda a, b : a * b\n",
"print(x(5, 6))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "aDqPyIqu5CuI",
"outputId": "7d5d3782-2ee6-4605-8b6f-11d3e045e5c1"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"30\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"x = lambda a, b, c : a + b + c\n",
"print(x(5, 6, 2))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8uPKSARX5Cxa",
"outputId": "d17f1751-33f6-4c6c-ca98-dddcd6ad46de"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"13\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"def myfunc(n):\n",
" return lambda a : a * n\n",
"\n",
"mydoubler = myfunc(2)\n",
"\n",
"print(mydoubler(11))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "nuxBpR5m5C2A",
"outputId": "88533027-bb58-43c2-a99e-06a285fda9c3"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"22\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"(lambda x: x + 1)(2)"
],
"metadata": {
"id": "lOLySgDB5C69",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "0e4bd7c4-f4cd-4176-deb1-a547f5ee07d1"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"3"
]
},
"metadata": {},
"execution_count": 5
}
]
},
{
"cell_type": "code",
"source": [
"add_one = lambda x: x + 1\n",
"add_one(2)"
],
"metadata": {
"id": "fd-X7WcP5C90",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "e4ddb639-5785-4fe2-c7ee-7e33d44f48c0"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"3"
]
},
"metadata": {},
"execution_count": 6
}
]
},
{
"cell_type": "code",
"source": [
"full_name = lambda first, last: f'Full name: {first.title()} {last.title()}'\n",
"full_name('guido', 'van rossum')"
],
"metadata": {
"id": "W_MPkFRf5DA0",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 36
},
"outputId": "376169c9-ed9e-4a7f-898f-dbb7332ab6d3"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'Full name: Guido Van Rossum'"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
}
},
"metadata": {},
"execution_count": 7
}
]
},
{
"cell_type": "code",
"source": [
"x =\"Cyrus Hi\"\n",
"\n",
"# lambda gets pass to print\n",
"(lambda x : print(x))(x)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "NJDzXvUDH-6-",
"outputId": "7b5b2730-ab9f-45b4-96c2-2b2cd5c7fbf2"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cyrus Hi\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Program to filter out only the even items from a list\n",
"my_list = [1, 5, 4, 6, 8, 11, 3, 12, 0]\n",
"\n",
"new_list = list(filter(lambda x: (x%2 == 0) , my_list))\n",
"\n",
"print(new_list)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "NK3MLUGHH-49",
"outputId": "0a0cc8b9-236a-469d-e064-237dbaaeb7f0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[4, 6, 8, 12, 0]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Program to double each item in a list using map()\n",
"\n",
"my_list = [1, 5, 4, 6, 8, 11, 3, 12, 100]\n",
"\n",
"new_list = list(map(lambda x: x * 2 , my_list))\n",
"\n",
"print(new_list)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "-DuIxrjWH-1z",
"outputId": "94531726-2597-4ade-9582-f430bc64118b"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[2, 10, 8, 12, 16, 22, 6, 24, 200]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"sequences = [10,2,8,7,5,4,3,11,0, 1]\n",
"filtered_result = filter (lambda x: x > 4, sequences) \n",
"print(list(filtered_result))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QW5ait4tH-zb",
"outputId": "555cd116-b5ff-4943-8ff8-4901797d024b"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[10, 8, 7, 5, 11]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"square = lambda x : x * x\n",
"square(5)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "uyUaoQ_qH-xB",
"outputId": "c7f3c588-9143-4cc7-858a-64958e194558"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"25"
]
},
"metadata": {},
"execution_count": 15
}
]
},
{
"cell_type": "code",
"source": [
"greet = lambda name: print('Hello', name, '?') \n",
"greet('Cyrus')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "IgFkJHyQH-t7",
"outputId": "eb00ecd8-7a26-4fe8-92a6-2df9a9acddcb"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Hello Cyrus ?\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"`Lambda` are generally used when a function is needed temporarily for a short period of time, often to be used inside another function such as filter, map and reduce. \n",
"Using `lambda` function, you can define a function and call it immediately at the end of definition. This can’t be done with def functions"
],
"metadata": {
"id": "qclRG0orMrj_"
}
},
{
"cell_type": "code",
"source": [
"print((lambda x: x if(x > 10) else 10)(5))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "rn30HBAAMsVf",
"outputId": "f0dc936e-4d83-44b7-a607-12f7e88ffe51"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"10\n"
]
}
]
}
]
}