jonas/nlp-lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

minor adjustments

Browse Source
This commit is contained in:
Jonas Weinz 2018-06-10 15:06:45 +02:00
parent eaa40ec370
commit 5e2af0697e
1 changed files with 21 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
Project/simple_approach/simple_twitter_learning.ipynb
View File

@ -22,7 +22,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -36,7 +36,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -60,7 +60,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -76,7 +76,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -99,7 +99,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1191,7 +1191,7 @@
"[68733 rows x 9 columns]" "[68733 rows x 9 columns]"
] ]
}, },
"execution_count": 5, "execution_count": 6,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1210,7 +1210,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1229,7 +1229,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1247,7 +1247,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1264,7 +1264,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1277,18 +1277,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"mlb_multi = MultiLabelBinarizer()\n", "labels = [emoji2sent(latest(x)) for x in emojis]"
"mlb_single = MultiLabelBinarizer()\n",
"\n",
"multi_labels = mlb_multi.fit_transform(emojis)\n",
"single_labels = mlb_single.fit_transform(np.array([latest(x) for x in emojis]))\n",
"\n",
"mlb = mlb_single if SINGLE_LABEL else mlb_multi\n",
"labels = single_labels if SINGLE_LABEL else multi_labels"
] ]
}, },
{ {
@ -1300,7 +1293,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1341,7 +1334,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1350,16 +1343,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 13, "execution_count": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"y1_weights = np.array([(sum([emoji_weights[e] for e in e_list]) / len(e_list)) if len(e_list) > 0 else 0 for e_list in mlb.inverse_transform(y1)])" "y1_weights = np.array([(sum([emoji_weights[e] for e in e_list]) / len(e_list)) if len(e_list) > 0 else 0 for e_list in sent2emoji(y1)])"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1619,7 +1612,9 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# build a dataframe to visualize test results:\n", "# build a dataframe to visualize test results:\n",
"testlist = pd.DataFrame({'text': Xt1, 'teacher': (mlb_single if SINGLE_LABEL else mlb).inverse_transform(yt1), 'predict': (mlb_single if SINGLE_LABEL else mlb).inverse_transform(binary_pred)})" "testlist = pd.DataFrame({'text': Xt1, \n",
" 'teacher': mlb_single.inverse_transform(yt1) if SINGLE_LABEL else sent2emoji(yt1), \n",
" 'predict': mlb_single.inverse_transform(binary_pred) if SINGLE_LABEL else sent2emoji(binary_pred)})"
] ]
}, },
{ {
@ -2214,7 +2209,7 @@
" \n", " \n",
" binary_pred = np.array(binary_pred)\n", " binary_pred = np.array(binary_pred)\n",
" \n", " \n",
" display(Markdown(\"# \" + str((mlb_single if SINGLE_LABEL else mlb).inverse_transform(binary_pred))))\n", " display(Markdown(\"# \" + str(mlb_single.inverse_transform(binary_pred) if SINGLE_LABEL else sent2emoji(binary_pred))))\n",
"\n", "\n",
"b.on_click(handle_submit)\n", "b.on_click(handle_submit)\n",
" \n", " \n",